Control method and system of remote wind power anemometer

Abstract

The invention provides a control method and system for a remote wind power anemograph. The method comprises the steps that an acoustic resonance type ultrasonic anemorumbometer is matched with an interface of a wind turbine generator through a customized mounting bracket; configuring a TPU wireless communication module and an antenna, and connecting the TPU wireless communication module with the acoustic resonance type ultrasonic anemorumbometer through the antenna; acquiring measurement work data by using an acoustic resonance type ultrasonic anemorumbometer; denoising the wind speed and wind direction measurement data and the working state data to obtain preprocessed data; the preprocessed data are sent to a monitoring terminal through the TPU wireless communication module, and the working state of the acoustic resonance type ultrasonic anemorumbometer is determined through the monitoring terminal; and adjusting the state of the acoustic resonance type ultrasonic anemorumbometer according to the working state. The advanced measurement technology and the wireless communication technology are combined, so that the measurement precision and the real-time monitoring capability are improved, and the intelligent state adjustment is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of wind measurement, and in particular to a control method and system for a remote wind power anemometer. Background Art

[0002] Anemometers are important wind measurement components for wind turbines. Their primary function is to provide wind speed and direction signals to ensure safe operation and power generation efficiency. However, traditional mechanical anemometers have the following problems in practical applications:

[0003] Winter icing problem: Mechanical anemometers are prone to failure due to ice or snow in cold areas, resulting in inaccurate measurement data or even failure to work.

[0004] Mechanical wear and failure: Mechanical anemometers rely on rotating parts, which are prone to wear, jamming and other problems after long-term operation, increasing maintenance costs.

[0005] Maintenance difficulties and risks: Maintenance of traditional anemometers requires operators to climb towers, which poses a high safety risk, especially in severe weather conditions.

[0006] Insufficient data transmission and monitoring: Traditional anemometers lack remote monitoring and adjustment functions and cannot meet the needs of intelligent operation and maintenance of modern wind farms.

[0007] To address these issues, ultrasonic anemometers are gradually becoming an alternative. They utilize a non-contact measurement principle, transmitting ultrasonic pulses and receiving echoes, calculating wind speed and direction using the time difference. This fundamentally avoids mechanical wear and icing. However, existing ultrasonic anemometers still have shortcomings in remote control and data transmission, particularly in terms of reliability and functional integration for medium- and long-range wireless communications. Summary of the Invention

[0008] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide a control method and system for a remote wind turbine anemometer. By combining advanced measurement technology and wireless communication technology, it not only improves the measurement accuracy and real-time monitoring capability, but also realizes intelligent state adjustment, reduces operation and maintenance costs and risks, enhances the reliability of the system, and has significant economic and social benefits.

[0009] To achieve the above object, the present invention provides the following solutions:

[0010] A control method for a remote wind power anemometer, comprising:

[0011] Match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket;

[0012] Configure a TPUNB wireless communication module and an antenna, and connect the TPUNB wireless communication module to the acoustic resonance ultrasonic anemometer through the antenna;

[0013] Use acoustic resonance ultrasonic wind speed and direction meter to collect measurement data;

[0014] Performing denoising processing on the wind speed and direction measurement data and the working status data to obtain preprocessed data;

[0015] The pre-processed data is sent to a monitoring terminal through the TPUNB wireless communication module, and the working state of the acoustic resonance type ultrasonic anemometer is determined through the monitoring terminal;

[0016] The state of the acoustic resonance type ultrasonic anemometer is adjusted according to the working state.

[0017] Preferably, the measurement working data includes: wind speed signal, wind direction signal, equipment temperature signal and equipment power signal.

[0018] Preferably, performing denoising processing on the wind speed and direction measurement data and the working status data to obtain preprocessed data includes:

[0019] Shifting the signal of the working status data to obtain a shifted signal;

[0020] performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0021] Determine the filtering threshold according to the decomposition scale and length of the signal;

[0022] Constructing a denoising function according to the filtering threshold;

[0023] The denoising function is used to remove noise from the translated signal to obtain preprocessed data.

[0024] Preferably, the formula for the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the shifted signal, d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

[0025] Preferably, removing noise from the shifted signal using the denoising function to obtain preprocessed data comprises:

[0026] The corresponding wavelet coefficients are removed using the denoising function to obtain multiple smoothed signals; wherein the denoising function is: Among them, X represents the wavelet coefficient, n represents the adjustment coefficient;

[0027] Performing an inverse translation on the smoothed signal to obtain an inverse translated signal;

[0028] An average of a plurality of inverse-translated signals is obtained to obtain the preprocessed data.

[0029] Preferably, determining the working status of the acoustic resonance ultrasonic anemometer by the monitoring terminal includes:

[0030] A deep learning model is installed in the monitoring terminal;

[0031] Acquire a training sample set; the training sample set includes a device temperature data set and a device power data set;

[0032] Training the deep learning model according to the temperature dataset and the device power dataset respectively to obtain a trained first classifier and a trained second classifier;

[0033] Cascading the trained first classifier and the second classifier to obtain a classification network;

[0034] Connecting the trained LSTM neural network after the classification network to obtain the working status evaluation model;

[0035] The pre-processed data is sent to the working status evaluation model to obtain the working status of the acoustic resonance ultrasonic anemometer; the working status includes normal operation, slight abnormality and serious abnormality.

[0036] Preferably, the deep learning model includes two stacked convolutional layers, a ReLU activation function and a pooling layer arranged in sequence.

[0037] Preferably, the state of the acoustic resonance type ultrasonic anemometer is adjusted according to the working state.

[0038] When the working state is normal operation, the state of the acoustic resonance type ultrasonic anemometer is monitored in real time;

[0039] When the working state is slightly abnormal, the parameter optimization logic is triggered, and the operating parameters of the acoustic resonance type ultrasonic anemometer are adjusted by the parameter optimization logic;

[0040] When the working state is seriously abnormal, the alarm mechanism is triggered and the protection logic of the acoustic resonance type ultrasonic anemometer is executed at the same time.

[0041] A control system for a remote wind turbine anemometer, comprising:

[0042] Installation module, used to match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket;

[0043] A configuration module, configured to configure a TPUNB wireless communication module and an antenna, and connect the TPUNB wireless communication module to the acoustic resonance ultrasonic anemometer through the antenna;

[0044] An acquisition module is used to collect measurement data using an acoustic resonance ultrasonic wind speed and direction meter;

[0045] A preprocessing module, configured to perform denoising on the wind speed and direction measurement data and the working status data to obtain preprocessed data;

[0046] A state determination module, configured to send the pre-processed data to a monitoring terminal via the TPUNB wireless communication module, and determine the working state of the acoustic resonance ultrasonic anemometer via the monitoring terminal;

[0047] The adjustment module is used to adjust the state of the acoustic resonance ultrasonic anemometer according to the working state.

[0048] Preferably, the preprocessing module includes:

[0049] a signal shifting unit, configured to shift the signal of the working status data to obtain a shifted signal;

[0050] A wavelet decomposition unit, configured to perform wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0051] A threshold determination unit, configured to determine a filtering threshold according to a decomposition scale and length of the signal;

[0052] A function construction unit, configured to construct a denoising function according to the filtering threshold;

[0053] The noise removal unit is used to remove noise from the shifted signal using the denoising function to obtain preprocessed data.

[0054] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0055] The present invention provides a control method and system for a remote wind turbine anemometer, comprising: matching an acoustic resonance ultrasonic anemometer with an interface of a wind turbine generator set via a customized mounting bracket; configuring a TPUNB wireless communication module and an antenna, and connecting the TPUNB wireless communication module to the acoustic resonance ultrasonic anemometer via the antenna; collecting measurement data using the acoustic resonance ultrasonic anemometer; performing denoising on the wind speed and direction measurement data and the working status data to obtain preprocessed data; transmitting the preprocessed data to a monitoring terminal via the TPUNB wireless communication module, and determining the working status of the acoustic resonance ultrasonic anemometer via the monitoring terminal; and adjusting the state of the acoustic resonance ultrasonic anemometer according to the working status. By combining advanced measurement technology with wireless communication technology, the present invention not only improves measurement accuracy and real-time monitoring capabilities, but also implements intelligent state adjustment, reduces operation and maintenance costs and risks, enhances system reliability, and has significant economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A flow chart of a method provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the system structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] The purpose of the present invention is to provide a control method and system for a remote wind turbine anemometer. By combining advanced measurement technology and wireless communication technology, it not only improves measurement accuracy and real-time monitoring capabilities, but also realizes intelligent state adjustment, reduces operation and maintenance costs and risks, enhances system reliability, and has significant economic and social benefits.

[0061] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0062] Figure 1 A flow chart of the method provided in the embodiment of the present invention is shown in FIG. Figure 1 As shown, the present invention provides a control method for a remote wind turbine anemometer, comprising:

[0063] Step 100: Match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket;

[0064] Step 200: Configure a TPUNB wireless communication module and an antenna, and connect the TPUNB wireless communication module to the acoustic resonance ultrasonic anemometer through the antenna;

[0065] Step 300: Collecting measurement data using an acoustic resonance ultrasonic anemometer;

[0066] Step 400: performing denoising processing on the wind speed and direction measurement data and the working status data to obtain pre-processed data;

[0067] Step 500: sending the pre-processed data to the monitoring terminal via the TPUNB wireless communication module, and determining the working status of the acoustic resonance ultrasonic anemometer via the monitoring terminal;

[0068] Step 600: Adjust the state of the acoustic resonance ultrasonic anemometer according to the working state.

[0069] Specifically, step 100 of this embodiment includes:

[0070] Step 1: Preparation and equipment selection

[0071] Before installing the acoustic resonance ultrasonic anemometer, a site survey is required to confirm the wind turbine's mounting interface type. Based on project requirements, a custom tubular mounting bracket suitable for the Goldwind GW82-1500 and Dongfang Turbine's FD82B-1500 turbines is selected. This bracket must fully mate with the anemometer's interface to facilitate subsequent installation and commissioning. The mounting bracket's design takes into account equipment stability and electrical conductivity, ensuring a good electrical connection between the bracket and the lightning protection assembly during installation.

[0072] Step 2: Fixing and connecting the mounting bracket

[0073] After confirming that the bracket matches the wind turbine interface, secure the bracket. Securely attach the customized mounting bracket to the wind turbine's lightning protection assembly using bolts or other fixing methods. During installation, ensure electrical continuity between the bracket's mounting surface and the lightning protection assembly. Apply conductive paste if necessary to enhance conductivity. After installation, check the bracket's stability to ensure it can withstand the weight of the anemometer and the external environment.

[0074] Step 3: Installation and debugging of acoustic resonance ultrasonic anemometer

[0075] Connect the acoustic resonance ultrasonic anemometer to the mounting bracket via a dedicated cable. Insert the cable through the lightning protection assembly duct outside the nacelle, ensuring the cable length is appropriate for easy connection. When connecting, ensure the mechanical zero point of the ultrasonic anemometer is toward the rear of the nacelle to ensure measurement accuracy. After connection, tighten the connection to ensure a secure connection. Finally, perform an electrical test to confirm that the electrical interface between the anemometer and wind direction and the wind turbine is functioning properly, ensuring reliable data transmission and preparing for subsequent commissioning and operation.

[0076] Furthermore, step 200 of this embodiment includes:

[0077] Step 1: Choose a suitable installation location

[0078] Before configuring the TPUNB wireless communication module, you must first select a suitable installation location. The TPUNB wireless communication module should be installed away from high-voltage power supply channels to prevent electromagnetic interference from affecting communication signals. The module should be mounted as close as possible to the acoustic resonance ultrasonic anemometer to minimize signal transmission distance and latency. During installation, ensure that the module's flat mounting structure is securely fastened to the DIN rail to facilitate subsequent maintenance and commissioning.

[0079] Step 2: Connect the wireless communication module to the anemometer

[0080] The TPUNB wireless communication module connects to the acoustic resonance ultrasonic anemometer via the RS485 communication port. First, connect the wireless communication module's power cables (24V DC+ and 0V) to a power source to ensure proper power. Then, use the RS485 communication cable to connect the wireless communication module to the anemometer's communication port. During wiring, ensure the correct wiring sequence and avoid reverse polarity to ensure stable and reliable communication.

[0081] Step 3: Install the antenna and test the signal

[0082] The TPUNB wireless communication module's antenna has a magnetic mount. During installation, attach the antenna to the top of the control cabinet, ensuring it does not interfere with other moving parts (such as the crane truss). The antenna should be installed away from obstructions to ensure optimal signal reception and transmission. After antenna installation, perform a wireless communication signal test to ensure proper signal transmission between the module and the anemometer. During this test, personnel should check the strength and stability of the wireless communication signal from within the cabin to ensure smooth data transmission.

[0083] Step 4: Configure the visual debugging software

[0084] After the wireless communication module and antenna are installed, the corresponding visual debugging software must be configured to enable remote monitoring and parameter adjustment of the anemometer. This software should display real-time data such as wind speed, wind direction, and device temperature, and provide the ability to adjust the anemometer heater power. This software allows operations and maintenance personnel to conveniently monitor device status and diagnose faults without being onboard, ensuring safe and stable operation of the wind turbine. After completing software configuration, a final system test is performed to ensure that all functions are functioning properly.

[0085] Preferably, the measurement working data includes: wind speed signal, wind direction signal, equipment temperature signal and equipment power signal.

[0086] Specifically, the acoustic resonance ultrasonic anemometer transmits ultrasonic pulses and receives their echoes, using the time difference to calculate wind speed and direction. During this process, the instrument monitors ambient temperature and device power in real time to ensure data accuracy and reliability. The collected wind speed and direction signals are transmitted to the TPUNB wireless communication module via the RS485 communication interface. Device temperature and power signals are also transmitted simultaneously. After data transmission, the TPUNB module sends these signals to the monitoring terminal. Operations and maintenance personnel can view and analyze these measurement data in real time using visual monitoring software to ensure the normal operation and efficient power generation of the wind turbine.

[0087] Preferably, performing denoising processing on the wind speed and direction measurement data and the working status data to obtain preprocessed data includes:

[0088] Shifting the signal of the working status data to obtain a shifted signal;

[0089] performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0090] Determine the filtering threshold according to the decomposition scale and length of the signal;

[0091] Constructing a denoising function according to the filtering threshold;

[0092] The denoising function is used to remove noise from the translated signal to obtain preprocessed data.

[0093] Preferably, the formula for the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the shifted signal, d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

[0094] Specifically, in the wavelet threshold denoising process, the quality of threshold selection directly affects the denoising effect. Since the amplitude of the noise wavelet coefficient decreases with the increase of the decomposition scale, this embodiment introduces the decomposition scale to adaptively adjust the filtering threshold.

[0095] Preferably, removing noise from the shifted signal using the denoising function to obtain preprocessed data comprises:

[0096] The corresponding wavelet coefficients are removed using the denoising function to obtain multiple smoothed signals; wherein the denoising function is: Among them, X represents the wavelet coefficient, n represents the adjustment coefficient;

[0097] Performing an inverse translation on the smoothed signal to obtain an inverse translated signal;

[0098] An average of a plurality of inverse-translated signals is obtained to obtain the preprocessed data.

[0099] Furthermore, this embodiment uses wavelet coefficients to measure the attenuation deviation, so that the attenuation of wavelet coefficients with larger absolute values ​​decreases as their absolute values ​​increase, thereby effectively avoiding the loss of high-frequency information and improving the signal-to-noise ratio.

[0100] Preferably, determining the working status of the acoustic resonance ultrasonic anemometer by the monitoring terminal includes:

[0101] A deep learning model is installed in the monitoring terminal;

[0102] Acquire a training sample set; the training sample set includes a device temperature data set and a device power data set;

[0103] Training the deep learning model according to the temperature dataset and the device power dataset respectively to obtain a trained first classifier and a trained second classifier;

[0104] Cascading the trained first classifier and the second classifier to obtain a classification network;

[0105] Connecting the trained LSTM neural network after the classification network to obtain the working status evaluation model;

[0106] The pre-processed data is sent to the working status evaluation model to obtain the working status of the acoustic resonance ultrasonic anemometer; the working status includes normal operation, slight abnormality and serious abnormality.

[0107] Optionally, step 500 of this embodiment includes:

[0108] Step 1: Building and training a deep learning model

[0109] To implement a deep learning model in a monitoring terminal, it is first necessary to prepare a training sample set, including a device temperature dataset and a device power dataset. By collecting and labeling historical data of the anemometer under different operating conditions, a sample set containing three states: normal operation, slight anomalies, and severe anomalies is constructed. Then, the temperature dataset and power dataset are used to train the deep learning model, respectively, to obtain two independent classifiers (the first classifier and the second classifier). During the training process, the cross-validation method is used to optimize the model parameters to ensure the accuracy and robustness of the classifier. After training is completed, the two classifiers are cascaded to form a complete classification network, which is used to preliminarily judge the operating status of the anemometer.

[0110] Step 2: Training and integration of LSTM neural network

[0111] Based on the classification network, a trained LSTM (Long Short-Term Memory) neural network is further connected to analyze the dynamic changes in time series data. The LSTM neural network is trained using real-time operating data from anemometers, including time series of wind speed, direction, device temperature, and power. By learning from this data, the LSTM can capture changing trends and potential abnormal patterns in the device's operating status. After training, the LSTM neural network is integrated with the classification network to form a complete operating status assessment model capable of accurately assessing the operating status of anemometers.

[0112] Step 3: Real-time data input and status assessment

[0113] In actual operation, preprocessed data collected by the anemometer (including wind speed, wind direction, device temperature, and power signals) is transmitted to the monitoring terminal via the TPUNB wireless communication module. The monitoring terminal inputs this data into the operating status assessment model. The classification network first performs a preliminary classification of the data to determine whether the device is in normal operation, a minor anomaly, or a serious anomaly. An LSTM neural network then further analyzes the time series data to verify the accuracy of the classification results and outputs the final operating status assessment results. Based on the evaluation results, the monitoring terminal can trigger appropriate adjustment logic or alarm mechanisms to ensure stable operation and timely maintenance of the anemometer.

[0114] Preferably, the deep learning model includes two stacked convolutional layers, a ReLU activation function and a pooling layer arranged in sequence.

[0115] Preferably, the state of the acoustic resonance type ultrasonic anemometer is adjusted according to the working state.

[0116] When the working state is normal operation, the state of the acoustic resonance type ultrasonic anemometer is monitored in real time;

[0117] When the working state is slightly abnormal, the parameter optimization logic is triggered, and the operating parameters of the acoustic resonance type ultrasonic anemometer are adjusted by the parameter optimization logic;

[0118] When the working state is seriously abnormal, the alarm mechanism is triggered and the protection logic of the acoustic resonance type ultrasonic anemometer is executed at the same time.

[0119] Furthermore, step 600 of this embodiment includes:

[0120] Step 1: Real-time monitoring of normal operating status

[0121] When the working status assessment model determines that the acoustic resonance ultrasonic anemometer is operating normally, the system enters real-time monitoring mode. Through the TPUNB wireless communication module, the anemometer's operating data (including wind speed, wind direction, device temperature, and power signals) is continuously transmitted to the monitoring terminal. The monitoring terminal displays this data in real time using visualization software and records it to the cloud or local server for subsequent analysis. At the same time, the system regularly denoises the data to ensure the accuracy and reliability of the monitoring data. In this state, the device does not require parameter adjustment; it only needs to maintain the stability of data acquisition and transmission to ensure the normal operation of the wind turbine.

[0122] Step 2: Parameter optimization for slightly abnormal conditions

[0123] When the working status assessment model detects a slight anomaly (such as high equipment temperature, abnormal power, or abnormal fluctuations in wind speed and direction signals), the system triggers the parameter optimization logic. First, the monitoring terminal analyzes the specific cause based on the type of anomaly. For example, high temperature may be caused by changes in ambient temperature or excessive heating power of the equipment. Subsequently, the system sends adjustment instructions to the anemometer through the TPUNB wireless communication module to dynamically optimize the operating parameters. For example, when the equipment temperature is high, the system will reduce the heater power; when the wind speed and direction signals fluctuate abnormally, the system will adjust the installation angle offset or recalibrate the measurement benchmark. After the parameter optimization is completed, the system will continue to monitor the equipment status to ensure that the anomaly is effectively alleviated.

[0124] Step 3: Alarm and protection of serious abnormal conditions

[0125] When the working status assessment model determines that the equipment is in a serious abnormal state (such as communication interruption, equipment failure or complete signal loss), the system will immediately trigger the alarm mechanism and execute the protection logic. The alarm mechanism includes sending high-priority alarms to the monitoring terminal and notifying the operation and maintenance personnel via SMS or email. The protection logic takes corresponding measures based on the type of abnormality, such as turning off the heater to prevent the equipment from overheating, or disconnecting the power supply to the equipment to avoid further damage. In addition, the system will record detailed information about the abnormal state, including time, abnormality type and related data, for subsequent fault analysis and maintenance. After the alarm and protection logic are executed, the system will enter a standby state, waiting for manual intervention or further instructions.

[0126] Corresponding to the above method, such as Figure 2 As shown, this embodiment also provides a control system for a remote wind turbine anemometer, including:

[0127] Installation module, used to match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket;

[0128] A configuration module, configured to configure a TPUNB wireless communication module and an antenna, and connect the TPUNB wireless communication module to the acoustic resonance ultrasonic anemometer through the antenna;

[0129] An acquisition module is used to collect measurement data using an acoustic resonance ultrasonic wind speed and direction meter;

[0130] A preprocessing module, configured to perform denoising on the wind speed and direction measurement data and the working status data to obtain preprocessed data;

[0131] A state determination module, configured to send the pre-processed data to a monitoring terminal via the TPUNB wireless communication module, and determine the working state of the acoustic resonance ultrasonic anemometer via the monitoring terminal;

[0132] The adjustment module is used to adjust the state of the acoustic resonance ultrasonic anemometer according to the working state.

[0133] Preferably, the preprocessing module includes:

[0134] a signal shifting unit, configured to shift the signal of the working status data to obtain a shifted signal;

[0135] A wavelet decomposition unit, configured to perform wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients;

[0136] A threshold determination unit, configured to determine a filtering threshold according to a decomposition scale and length of the signal;

[0137] A function construction unit, configured to construct a denoising function according to the filtering threshold;

[0138] The noise removal unit is used to remove noise from the shifted signal using the denoising function to obtain preprocessed data.

[0139] The beneficial effects of the present invention are as follows:

[0140] (1) The present invention uses an acoustic resonance ultrasonic anemometer to achieve non-contact measurement, avoiding the wear and icing problems of traditional mechanical instruments, thereby improving the measurement accuracy of wind speed and direction.

[0141] (2) After configuring the TPUNB wireless communication module, the present invention can realize the remote transmission of real-time data. Operation and maintenance personnel can monitor the working status of the anemometer at any time and obtain important data such as wind speed, wind direction, equipment temperature and power in a timely manner, thereby enhancing the management capability of the wind farm.

[0142] (3) The present invention can achieve intelligent state adjustment of the anemometer by denoising the measured data and evaluating the working status. For example, the heater power can be automatically adjusted according to changes in the device temperature and power signal to ensure normal operation of the device under various environmental conditions.

[0143] (4) The remote monitoring and status adjustment functions of the present invention reduce the frequency of on-site inspections by operation and maintenance personnel, reduce labor costs and safety risks, and especially reduce the need for tower climbing operations under severe weather conditions.

[0144] (5) Through real-time monitoring and fault diagnosis, the present invention can promptly detect and handle equipment anomalies, thereby improving the overall reliability of the system and ensuring the safe and stable operation of the wind turbine.

[0145] (6) The present invention can provide data support for optimizing the operation strategy of wind farms by storing and analyzing long-term operation data, thereby further improving power generation efficiency and economic benefits.

[0146] (7) The present invention can adapt to the wind speed and direction measurement needs under different environmental conditions, especially in extreme environments such as high cold and humidity, ensuring the stability and reliability of the equipment.

[0147] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0148] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A control method for a remote wind power anemometer, characterized in that: include: Match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket; Configure a TPUNB wireless communication module and an antenna, and connect the TPUNB wireless communication module to the acoustic resonance type ultrasonic anemometer through the antenna; Use acoustic resonance ultrasonic wind speed and direction instrument to collect measurement data; De-noising the wind speed and direction measurement data and the working status data to obtain pre-processed data; The pre-processed data is sent to a monitoring terminal through the TPUNB wireless communication module, and the working state of the acoustic resonance type ultrasonic anemometer is determined through the monitoring terminal; The state of the acoustic resonance type ultrasonic anemometer is adjusted according to the working state.

2. The control method of the remote wind power anemometer according to claim 1, characterized in that: The measurement working data includes: wind speed signal, wind direction signal, equipment temperature signal and equipment power signal.

3. The control method of the remote wind power anemometer according to claim 1, characterized in that: De-noising the wind speed and direction measurement data and the working status data to obtain pre-processed data, including: Shifting the signal of the working status data to obtain a shifted signal; Performing wavelet decomposition on the shifted signal to obtain a plurality of wavelet coefficients; Determine the filtering threshold according to the decomposition scale and length of the signal; Constructing a denoising function according to the filtering threshold; The denoising function is used to remove noise from the translated signal to obtain preprocessed data.

4. The control method of the remote wind power anemometer according to claim 3 is characterized in that: The formula for the filtering threshold is: Among them, λ is the filtering threshold, j is the decomposition scale of the translated signal, and d j is the decomposition of the wavelet coefficients with a scale of j, N represents the length of the shifted signal, and median represents the median operation.

5. The control method of the remote wind power anemometer according to claim 4, characterized in that: Using the denoising function to remove the noise of the translated signal to obtain preprocessed data includes: The corresponding wavelet coefficients are removed by using the denoising function to obtain a plurality of smoothed signals; wherein the denoising function is: Among them, X represents the wavelet coefficient, n represents the adjustment coefficient; Performing inverse translation on the smoothed signal to obtain an inverse translated signal; The preprocessed data is obtained by averaging a plurality of inverse-translated signals.

6. The control method of the remote wind power anemometer according to claim 2, characterized in that: Determining the working state of the acoustic resonance type ultrasonic anemometer through the monitoring terminal includes: A deep learning model is installed in the monitoring terminal; Acquire a training sample set; the training sample set includes a device temperature data set and a device power data set; The deep learning model is trained according to the temperature data set and the device power data set respectively to obtain a trained first classifier and a second classifier; Cascading the trained first classifier and the second classifier to obtain a classification network; Connecting the trained LSTM neural network after the classification network to obtain the working status evaluation model; The pre-processed data is sent to the working status evaluation model to obtain the working status of the acoustic resonance ultrasonic anemometer; the working status includes normal operation, slight abnormality and serious abnormality.

7. The control method of the remote wind power anemometer according to claim 6, characterized in that: The deep learning model includes two stacked convolutional layers, a ReLU activation function and a pooling layer arranged in sequence.

8. The control method of the remote wind power anemometer according to claim 1, characterized in that: The state of the acoustic resonance type ultrasonic anemometer is adjusted according to the working state. When the working state is normal operation, the state of the acoustic resonance type ultrasonic anemometer is monitored in real time; When the working state is slightly abnormal, the parameter optimization logic is triggered, and the operating parameters of the acoustic resonance type ultrasonic anemometer are adjusted by the parameter optimization logic; When the working state is seriously abnormal, the alarm mechanism is triggered and the protection logic of the acoustic resonance type ultrasonic anemometer is executed at the same time.

9. A control system for a remote wind turbine anemometer, characterized in that: include: Installation module, used to match the acoustic resonance ultrasonic anemometer with the interface of the wind turbine through a customized mounting bracket; A configuration module, used for configuring a TPUNB wireless communication module and an antenna, and connecting the TPUNB wireless communication module to the acoustic resonance type ultrasonic anemometer through the antenna; An acquisition module is used to acquire measurement data using an acoustic resonance ultrasonic wind speed and direction meter; A preprocessing module, used for performing denoising on the wind speed and direction measurement data and the working status data to obtain preprocessed data; A state determination module, used for sending the pre-processed data to a monitoring terminal through the TPUNB wireless communication module, and determining the working state of the acoustic resonance type ultrasonic anemometer through the monitoring terminal; The regulating module is used to regulate the state of the acoustic resonance type ultrasonic anemometer according to the working state.

10. The control system of the remote wind turbine anemometer according to claim 9, characterized in that: The preprocessing module comprises: A signal translation unit, used for translating the signal of the working status data to obtain a translated signal; A wavelet decomposition unit, used for performing wavelet decomposition on the translated signal to obtain a plurality of wavelet coefficients; A threshold determination unit, used to determine a filtering threshold according to a decomposition scale and a length of a signal; A function construction unit, used to construct a denoising function according to the filtering threshold; The noise removal unit is used to remove the noise of the translated signal by using the denoising function to obtain preprocessed data.

Images