A wind turbine monitoring and early warning system based on internet of things sensing technology

Abstract

The application discloses a kind of wind turbine monitoring early warning systems based on internet of things sensing technology, it is related to internet of things technical field, including data acquisition module: the operating state information of wind turbine key components is collected in real time, operating state data is sent to edge computing unit;Prediction module: identify abnormal mode, combine fast fourier transform analysis vibration signal time domain and frequency domain features, detect mechanical failure, and get residual life prediction value according to residual life prediction model;Preliminary warning module: based on fuzzy reasoning determines equipment health status score, and makes preliminary warning according to equipment health status score locally;Hierarchical warning module: according to mechanical failure condition, combined with equipment health status score, wind turbine equipment is classified alarm, and maintenance decision suggestion is provided.Integrating internet of things technology, edge computing, artificial intelligence, realize the intelligent monitoring and early warning of wind turbine, improve the reliability and safety of equipment operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things, more particularly, the present application relates to a wind turbine monitoring and early warning system based on Internet of Things sensing technology. BACKGROUND

[0002] Wind power, as an important part of clean energy, has been rapidly developing in recent years. However, due to the long-term operation of wind turbines in high-altitude, offshore or remote areas, the equipment maintenance and monitoring of wind turbines face many challenges. The core components of wind turbines, such as gearboxes, main shafts, generators, and variable pitch systems, are subjected to complex mechanical loads, environmental influences (such as high wind speed, temperature change, humidity corrosion), and electrical stress for a long time, which are prone to fatigue damage, lubrication failure, electrical failure and other problems. These problems not only affect the efficiency of the wind turbine, but also may cause significant economic losses and safety hazards.

[0003] The existing technology has the following problems: traditional wind turbine operation and maintenance mainly rely on manual inspection and regular maintenance, but due to the large number of wind turbines and their wide distribution, manual operation and maintenance is costly, inefficient, and difficult to find potential faults in time. Therefore, how to use emerging technologies such as Internet of Things, artificial intelligence (AI), edge computing, etc. to improve the intelligent monitoring capability of wind turbines, reduce unplanned downtime, and optimize maintenance strategies has become a key problem to be solved in the wind power industry. The present application provides a wind turbine monitoring and early warning system based on Internet of Things sensing technology, which integrates Internet of Things technology, edge computing, artificial intelligence and remote expert system to realize intelligent monitoring and early warning of wind turbines and improve the reliability and safety of equipment operation.

[0004] To solve the above problems, the present application provides a solution. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a wind turbine monitoring and early warning system based on Internet of Things sensing technology, which solves the problems raised in the background art by using a wind turbine monitoring and early warning system based on Internet of Things sensing technology.

[0006] To achieve the above-mentioned purposes, the present application provides the following technical solutions:

[0007] A wind turbine monitoring and early warning system based on Internet of Things sensing technology, comprising:

[0008] A data acquisition module: real-time acquisition of operation state information of key components of a wind turbine, the operation state information including vibration signals and temperature data, and sending the operation state data to an edge computing unit using low-power wireless communication technology;

[0009] The prediction module: according to the neural network algorithm, the edge computing device is analyzed in real time, the abnormal mode is identified, the time domain and frequency domain characteristics of the vibration signal are analyzed by combining fast fourier transform (FTT), the mechanical fault is detected, and the residual life prediction (RUL) model is obtained according to the residual life prediction value;

[0010] The preliminary warning module: through the analysis of the residual life prediction and the abnormal mode, the device health state score is determined based on fuzzy reasoning, and the preliminary warning is made locally according to the device health state score;

[0011] The hierarchical warning module: according to the mechanical fault condition, the device health state score is combined, the wind turbine is monitored and analyzed by the remote diagnosis system, the wind turbine equipment is classified and alarmed according to the monitoring and analysis results, and the maintenance decision suggestion and response measures are provided.

[0012] In a preferred embodiment, the process of collecting the running state information of the key components of the wind turbine in real time is as follows:

[0013] Select the acceleration sensor suitable for vibration measurement of the key components of the wind turbine, install it in the appropriate position of the key components, and ensure that the vibration signal can be accurately captured;

[0014] Amplify and filter the analog signal output by the acceleration sensor to improve the signal quality and meet the input requirements of the analog-to-digital converter (ADC);

[0015] Install the temperature sensor on the surface of the key components to monitor the temperature change in real time; linearize and amplify the analog signal output by the temperature sensor, and send it to the ADC for digital conversion;

[0016] Use the ADC to convert the analog signal to a digital signal for subsequent processing and transmission.

[0017] In a preferred embodiment, the process of identifying abnormal patterns is as follows:

[0018] After preprocessing the running state information, a convolutional neural network is used for analysis to capture the local features of the signal;

[0019] Use cross-entropy loss function as the loss function of the convolutional neural network, and update the parameters of the neural network through the SGD optimizer;

[0020] Use the training set to train the neural network model, update the parameters of the model through iteration, and minimize the value of the loss function;

[0021] Input the preprocessed running state information into the trained neural network model, and the model outputs the probability of each sample belonging to the abnormal mode;

[0022] According to the comparison of the abnormal mode probability and the set abnormal threshold, it is judged whether the sample is an abnormal mode.

[0023] In a preferred embodiment, the detection mechanical failure process is as follows:

[0024] In combination with the time domain and frequency domain characteristics obtained by FFT analysis and the output result of the neural network model, it is judged whether the key components of the wind turbine exist mechanical failure;

[0025] If the main frequency of the vibration signal changes abnormally, and the abnormal probability output by the neural network model exceeds the threshold value, it is considered that there is mechanical failure.

[0026] In a preferred embodiment, the residual life prediction value acquisition process is as follows:

[0027] Select the time domain and frequency domain characteristics of the vibration signal as the input of the RUL model;

[0028] Use the historical operation data and the corresponding residual life label to train the RUL model;

[0029] After training, input the real-time collected operation state information into the RUL model, and output the residual life prediction value of the device.

[0030] In a preferred embodiment, the device health state score determination process based on fuzzy inference is as follows:

[0031] Define the abnormal mode probability and the residual life prediction value as input variables, and divide them into different fuzzy sets respectively;

[0032] Define the device health state score as an output variable, divide it into a fuzzy set, develop fuzzy rules, and describe the influence of the abnormal mode probability and the residual life prediction value on the device health state score;

[0033] According to the fuzzy rules, the device health state score is determined by fuzzy inference.

[0034] In a preferred embodiment, the preliminary warning process made locally according to the device health state score is as follows:

[0035] When the device health state score is greater than the preset health threshold, it indicates that the device health state is good, and no preliminary warning is needed,

[0036] When the device health state score is less than the preset health threshold, it indicates that the device health state is not good, and preliminary warning is needed.

[0037] In a preferred embodiment, the remote monitoring and analysis process of the wind turbine is as follows:

[0038] According to the mechanical failure condition, the number of failures in a certain time period is obtained, the number of failures is divided by the time period to obtain the equipment failure rate, the equipment health state score is combined, and a monitoring evaluation coefficient is calculated based on a preset monitoring evaluation formula.

[0039] In a preferred embodiment, the process of grading alarm of wind turbine equipment according to the monitoring analysis result is as follows:

[0040] The monitoring evaluation coefficient is compared and analyzed with the preset first evaluation threshold and second evaluation threshold, and the first evaluation threshold is less than the second evaluation threshold.

[0041] If the monitoring evaluation coefficient is greater than the preset second evaluation threshold, the alarm level is a pre-warning level.

[0042] If the monitoring evaluation coefficient is greater than the preset first evaluation threshold and less than the second evaluation threshold, the alarm level is a warning level.

[0043] If the monitoring evaluation coefficient is less than the preset first evaluation threshold, the alarm level is an emergency level.

[0044] In a preferred embodiment, the process of providing maintenance decision suggestions and response measures is as follows:

[0045] If the alarm level is a pre-warning level, it indicates that there is a potential failure risk of the equipment, but it has not affected normal operation, and the operation data of the related components should be continuously monitored to ensure timely discovery of problems and arrangement of regular inspection to check the possible source of failure.

[0046] If the alarm level is a warning level, it indicates that the equipment has a more serious abnormality, and measures should be taken as soon as possible to check and diagnose the alarm components, adjust the operation conditions to delay the occurrence of failure, and reduce the risk.

[0047] If the alarm level is an emergency level, it indicates that the equipment has a serious failure, and the unit operation should be stopped immediately, and a maintenance team should be organized to carry out on-site fault diagnosis and repair to ensure the equipment to return to normal operation.

[0048] The technical effects and advantages of the wind turbine monitoring and early warning system based on the Internet of Things sensing technology are as follows:

[0049] 1.The application effectively solves the problems of slow response, high data transmission cost, and insufficient fault prediction capability of traditional fan monitoring systems through edge computing, health assessment, multi-modal sensor data fusion, and remote intelligent operation and maintenance. Since the traditional SCADA system relies on centralized processing, there is a large delay in data transmission and analysis, while the application can run the AI health assessment model locally through high-performance edge computing devices, achieving millisecond-level response, greatly improving the real-time performance of fan fault monitoring, and reducing the impact of sudden failures on fan operation. The traditional cloud-based PHM system requires transmission of a large amount of raw data, resulting in high bandwidth consumption, while the application uses an event-triggered data upload mechanism to upload only key feature data, reducing communication costs and improving system efficiency and reliability. In addition, existing monitoring solutions mostly rely on a single sensor type, which cannot accurately identify complex fault patterns, while the application uses multi-modal data fusion of vibration, temperature, current, acoustic, and visual data, combined with adaptive AI algorithms, to improve the accuracy of fault identification and reduce false positives and false negatives.

[0050] 2.The application uses high-performance embedded chips to support local health assessment model running, reduces dependence on the cloud, improves prediction accuracy and response speed. The AI algorithm based on FFT and CNN is run to intelligently predict and warn of faults in the operation of wind turbines. Local computing + remote optimization, the device can independently perform predictive maintenance analysis, while supporting remote expert system optimization of AI models to improve system adaptability. The use of multi-modal sensor data fusion technology improves fault identification accuracy and reduces false positives and false negatives. The device has a time synchronization mechanism to ensure the timeliness and consistency of various sensor data, improving monitoring accuracy. Edge computing is used to perform data analysis and fault detection locally, achieving millisecond-level response, reducing dependence on remote servers, and improving system reliability and independence. Through data preprocessing and noise reduction by the edge computing device, only key information is uploaded, reducing bandwidth consumption, and an event-triggered upload mechanism is used to upload detailed data only when an anomaly is detected, optimizing network utilization. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 A wind turbine monitoring and warning system based on Internet of Things sensing technology. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the application.

[0053] Embodiment 1, Figure 1 The application discloses a wind turbine monitoring and early warning system based on an Internet of Things sensing technology.

[0054] S10, real-time collection of operation state information of key components of a wind turbine, the operation state information including vibration signals and temperature data, and transmission of the operation state data to an edge computing unit by using low-power wireless communication technology;

[0055] Real-time access to various Internet of Things sensors, collection of operation state information of the wind turbine, selection of acceleration sensors suitable for vibration measurement of key components of the wind turbine, for example, piezoelectric acceleration sensors. The sensors are installed at appropriate positions of the key components (such as gearboxes and generator bearings) to ensure that the vibration signals can be accurately captured; the analog signals output by the acceleration sensors usually need to be amplified, filtered and the like to improve the signal quality and meet the input requirements of an analog-to-digital converter (ADC);

[0056] Temperature sensors such as thermocouples or thermistors are installed on the surface or inside the key components for real-time monitoring of temperature changes; the analog signals output by the temperature sensors need to be linearized, amplified and then sent to an ADC for digital conversion;

[0057] Suitable ADCs are used to convert the analog signals into digital signals for subsequent processing and transmission.

[0058] Microcontrollers (such as single-chip microcomputers) are used to control the ADCs to collect data and temporarily store the collected data in an on-chip or external memory; according to the Nyquist sampling theorem, the sampling frequency should be at least twice the highest frequency of the signal;

[0059] According to actual application scenarios and requirements, appropriate technologies including Bluetooth, ZigBee and LoRa are selected, the selected wireless communication modules are connected to the microcontrollers, and corresponding configurations are performed, including setting of a communication protocol, a frequency band and a baud rate; the microcontrollers encapsulate the collected operation state data in a format of a wireless communication protocol and send the operation state data to the edge computing unit through the wireless modules;

[0060] The edge computing unit receives the data through the wireless communication modules and analyzes the data according to the communication protocol to restore the original operation state data.

[0061] S20, real-time analysis of the edge computing device according to a neural network algorithm, identification of an abnormal mode, combination of fast Fourier transform (FFT) analysis of time domain and frequency domain characteristics of the vibration signals, detection of mechanical faults and obtaining of a residual useful life prediction value according to a residual useful life prediction (RUL) model;

[0062] After preprocessing the running state information, a convolutional neural network (CNN) is used for analysis to capture the local features of the signal.

[0063] An cross-entropy loss function is used as the loss function of the convolutional neural network to identify abnormal patterns, and the formula of the cross-entropy loss function is as follows: In the formula, L is the loss function value, N is the number of samples, C is the number of categories, y ij is the true label of the i-th sample, p ij is the predicted probability that the i-th sample belongs to the j-th category.

[0064] The parameters of the neural network are updated by the SGD optimizer.

[0065] The neural network model is trained using the training set, and the parameters of the model are updated iteratively to minimize the value of the loss function.

[0066] The preprocessed running state information is input into the trained neural network model, and the model outputs the probability that each sample belongs to an abnormal pattern. According to the comparison of the abnormal pattern probability and the set abnormal threshold, it is judged whether the sample is an abnormal pattern.

[0067] According to the fast Fourier transform analysis of the time domain characteristics of the vibration signal, the time domain analysis of the vibration signal is carried out, and the mean, root mean square value and peak value of the vibration signal are calculated.

[0068] The time domain vibration signal is converted into a frequency domain signal using fast Fourier transform (FFT), and the frequency components of the vibration signal are analyzed to obtain the frequency domain characteristics of the vibration signal.

[0069] The fast Fourier transform formula is as follows: In the formula, x(n) is the time domain signal, X(k) is the frequency domain signal, and N is the number of samples.

[0070] The time domain and frequency domain characteristics obtained by combining the FFT analysis and the output results of the neural network model are used to determine whether the key components of the wind turbine exist mechanical failure. If the main frequency of the vibration signal changes abnormally and the abnormal probability output by the neural network model exceeds the threshold value, it is considered that there is a mechanical failure.

[0071] The time domain and frequency domain characteristics of the vibration signal are selected as the input of the RUL model.

[0072] The RUL model is trained using historical operating data and corresponding remaining life labels.

[0073] After training, the real-time collected running state information is input into the RUL model, and the remaining life prediction value of the device is output.

[0074] The test set is used to evaluate the anomaly pattern recognition model and the RUL model, and the learning rate, the number of hidden layer neurons of the neural network model, or the more appropriate features are adjusted to improve the performance of the model.

[0075] S30, based on the fuzzy inference, the device health state score is determined through the analysis of the remaining life prediction and the anomaly pattern condition, and a preliminary warning is made locally according to the device health state score;

[0076] The step of determining the device health state score based on the fuzzy inference is as follows:

[0077] Step C1, the anomaly pattern probability and the remaining life prediction value are defined as input variables, and are divided into different fuzzy sets respectively.

[0078] For example, "Low", "Medium", "High" for the anomaly pattern probability, "Low", "Medium", "High" for the remaining life prediction value.

[0079] Step C2, the device health state score is defined as an output variable, and is divided into a fuzzy set, for example, "Low", "High" for the device health state score.

[0080] Step C3, a set of fuzzy rules is formulated to describe the influence of different input variables on the output variable. The definition of the rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0081] Let the anomaly pattern probability be I, the remaining life prediction value be B, and the device health state score be W, then the following rules can be defined:

[0082] Rule 1: IF (I is Low) AND (B is High) THEN (W is High)

[0083] Rule 2: IF (I is High) AND (B is Low) THEN (W is Low) ...

[0085] Step C4, according to the fuzzy rules, the fuzzy inference is carried out to determine the device health state score.

[0086] It should be noted that the division of the fuzzy set can be adjusted according to the actual situation. For example, although three fuzzy sets are taken as an example in this embodiment, the anomaly pattern probability and the remaining life prediction value and the device health state score can be divided into more than three sets to facilitate better precision adjustment.

[0087] Further, for the judgment of the equipment health state score, a threshold value can be set for judgment according to the actual situation, for example, when the abnormal mode probability exceeds 0.6, it is marked as "High", when the remaining life prediction value is higher than 80 years, it is marked as "High", and the like, which will not be repeated here.

[0088] When the equipment health state score is greater than the preset health threshold value, it indicates that the equipment health state is good, and no preliminary warning is needed,

[0089] When the equipment health state score is less than the preset health threshold value, it indicates that the equipment health state is not good, and a preliminary warning is needed.

[0090] S40, according to the mechanical failure condition, combining the equipment health state score, through the remote diagnosis system to monitor and analyze the wind turbine, according to the monitoring and analysis result, the wind turbine equipment is classified alarm, and the maintenance decision suggestion and response measures are provided;

[0091] According to the mechanical failure condition, the number of failures in a certain time period is obtained, the number of failures is divided by the time period to obtain the equipment failure rate, combining the equipment health state score, based on the preset monitoring evaluation formula, the monitoring evaluation coefficient is calculated, the specific calculation formula is as follows: P = u1*W + u2*Y; in the formula, P is the monitoring evaluation coefficient, W is the equipment health state score, u1 is the equipment health state score weight factor, Y is the equipment failure rate, u2 is the equipment failure rate weight factor, u1 is greater than 0, and u2 is less than 0.

[0092] The monitoring evaluation coefficient is compared and analyzed with the preset first evaluation threshold value and second evaluation threshold value, and the first evaluation threshold value is less than the second evaluation threshold value;

[0093] If the monitoring evaluation coefficient is greater than the preset second evaluation threshold value, the alarm level is the warning level;

[0094] If the monitoring evaluation coefficient is greater than the preset first evaluation threshold value and less than the second evaluation threshold value, the alarm level is the warning level;

[0095] If the monitoring evaluation coefficient is less than the preset first evaluation threshold value, the alarm level is the emergency level.

[0096] If the alarm level is the warning level, it indicates that there is a potential failure risk in the equipment, but it has not yet affected the normal operation. At this time, the following measures should be taken:

[0097] Monitoring and tracking: continuously monitor the operation data of related components to ensure timely discovery of problems.

[0098] Regular inspection: arrange regular inspection to check the possible source of failure.

[0099] Predictive Maintenance: Based on data analysis, predict the time when the equipment may fail, and prepare maintenance solutions in advance.

[0100] If the alarm level is warning, it means that the equipment has appeared more serious abnormalities, and measures need to be taken as soon as possible. The maintenance decision suggestions at this time include:

[0101] Immediate inspection and diagnosis: Detailed inspection and fault diagnosis of the alarm component, and positioning of the problem source.

[0102] Arrange maintenance: If the failure affects the efficiency of the equipment, arrange for maintenance.

[0103] Adjust the operating parameters: If possible, delay the failure by adjusting the operating conditions (such as reducing the load, adjusting the wind speed, etc.), and reduce the risk.

[0104] If the alarm level is emergency, it means that the equipment has occurred serious failure, which may cause equipment damage or safety accidents. The maintenance decision suggestions at this time include:

[0105] Immediately stop: To avoid further damage to the equipment or safety accidents, the unit should be immediately stopped.

[0106] Emergency troubleshooting: Quickly organize a maintenance team to conduct on-site fault diagnosis and repair to ensure the equipment returns to normal operation.

[0107] Safety guarantee: If the failure involves safety risks, safety guarantee measures should be taken immediately to ensure personnel safety.

[0108] The above formulas are all dimensionless to calculate their numerical values. The formula is obtained by collecting a large amount of data to simulate the most recent real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0109] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product, wholly or partially.

[0110] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0111] In addition, each function module in each embodiment of the present application can be integrated in one processing module, or each module can be physically present alone, or two or more modules can be integrated in one module.

[0112] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0113] Finally: the above is only a preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A wind turbine monitoring and early warning system based on Internet of Things sensing technology, characterized in that, Comprise: Data acquisition module: real-time acquisition of the operating state information of the key components of the wind turbine, the operating state information including vibration signals and temperature data, and sending the operating state data to the edge computing unit using low-power wireless communication technology; Prediction module: real-time analysis of the edge computing device based on a neural network algorithm, identification of abnormal patterns, analysis of time domain and frequency domain characteristics of vibration signals using fast Fourier transform (FTT), detection of mechanical faults, and obtaining of a residual life prediction value based on a residual life prediction (RUL) model; Preliminary warning module: based on the analysis of the residual life prediction and abnormal patterns, determining the equipment health state score based on fuzzy reasoning, and making a preliminary warning locally according to the equipment health state score; Hierarchical warning module: based on the mechanical fault condition and the equipment health state score, remotely monitoring and analyzing the wind turbine through a remote diagnosis system, classifying the wind turbine equipment according to the monitoring and analysis results, and providing maintenance decision suggestions and response measures; The process of detecting mechanical faults is as follows: Combining the time domain and frequency domain characteristics obtained by FFT analysis and the output results of the neural network model, it is determined whether the key components of the wind turbine have mechanical faults; If the main frequency of the vibration signal changes abnormally and the abnormal probability output by the neural network model exceeds the threshold value, it is considered that there is a mechanical fault; The process of obtaining the residual life prediction value is as follows: Selecting the time domain and frequency domain characteristics of the vibration signal as the input of the RUL model; Using historical operating data and corresponding residual life labels to train the RUL model; After training is completed, input the real-time collected operating state information into the RUL model to output the residual life prediction value of the equipment.

2. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 1, characterized in that, The process of real-time acquisition of the operating state information of the key components of the wind turbine is as follows: Select an acceleration sensor suitable for vibration measurement of the key components of the wind turbine and install it at a suitable position on the key components to ensure accurate capture of the vibration signal; Amplify and filter the analog signal output by the acceleration sensor to improve signal quality and meet the input requirements of the analog-to-digital converter (ADC); Install a temperature sensor on the surface of the key components to monitor temperature changes in real time; linearize and amplify the analog signal output by the temperature sensor and send it to the ADC for digital conversion; Use the ADC to convert the analog signal to a digital signal for subsequent processing and transmission.

3. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 2, characterized in that, The process of identifying abnormal patterns is as follows: After preprocessing the operating state information, analyze it using a convolutional neural network to capture local features of the signal; A cross-entropy loss function is used as the loss function of the convolutional neural network, and the cross-entropy loss function is calculated according to the following formula: ; wherein L is a loss function value, N is a sample quantity, C is a category quantity, is a true label of the i th sample, is a prediction probability of the i th sample belonging to the j th category. Update the parameters of the neural network through the SGD optimizer; Train the neural network model using the training set, and update the parameters of the model through iteration to minimize the value of the loss function; Input the preprocessed operating state information into the trained neural network model, and the model outputs the probability that each sample belongs to an abnormal pattern; According to the comparison of the abnormal pattern probability and the set abnormal threshold value, it is determined whether the sample is an abnormal pattern.

4. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 1, characterized in that, The steps of determining the equipment health state score based on fuzzy reasoning are as follows: The abnormal pattern probability and the remaining life prediction value are defined as input variables, and are divided into different fuzzy sets respectively; The equipment health state score is defined as an output variable, and is divided into a fuzzy set; Fuzzy rules are formulated to describe the influence of the abnormal pattern probability and the remaining life prediction value on the equipment health state score; Fuzzy reasoning is performed according to the fuzzy rules to determine the equipment health state score.

5. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 4, characterized in that, The preliminary warning process based on the equipment health state score is as follows: When the equipment health state score is greater than a preset health threshold, it indicates that the equipment health state is good, and no preliminary warning is needed, When the equipment health state score is less than the preset health threshold, it indicates that the equipment health state is poor, and a preliminary warning is needed.

6. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 5, characterized in that, The remote monitoring and analysis process of the wind turbine is as follows: According to the mechanical failure condition, the number of failures in a certain time period is obtained, the equipment failure rate is obtained by dividing the number of failures by the time period, the monitoring evaluation coefficient is calculated based on the preset monitoring evaluation formula combined with the equipment health state score, and the specific calculation formula is as follows: ; In the formula, P is the monitoring evaluation coefficient, W is the equipment health state score, is the equipment health state score weight factor, Y is the equipment failure rate, is the equipment failure rate weight factor, is greater than 0, is less than 0.

7. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 6, characterized in that, The grading alarm process of the wind turbine equipment according to the monitoring and analysis results is as follows: The monitoring evaluation coefficient is compared and analyzed with a preset first evaluation threshold and a second evaluation threshold, and the first evaluation threshold is less than the second evaluation threshold; If the monitoring evaluation coefficient is greater than the preset second evaluation threshold, the alarm level is a warning level; If the monitoring evaluation coefficient is greater than the preset first evaluation threshold and less than the second evaluation threshold, the alarm level is a warning level; If the monitoring evaluation coefficient is less than the preset first evaluation threshold, the alarm level is an emergency level.

8. The wind turbine monitoring and early warning system based on the Internet of Things sensing technology according to claim 7, characterized in that, The process of providing maintenance decision suggestions and response measures is as follows: If the alarm level is a warning level, it indicates that there is a potential risk of failure in the equipment, but it has not yet affected normal operation, and the operation data of the relevant components should be continuously monitored to ensure that problems are discovered in a timely manner and regular inspections are arranged to check the possible sources of failure; If the alarm level is a warning level, it indicates that the equipment has already appeared a more serious abnormality, and measures should be taken as soon as possible to check and diagnose the alarm components in detail, adjust the operating conditions to delay the occurrence of failure, and reduce the risk; If the alarm level is an emergency level, it indicates that the equipment has already occurred a serious failure, and the unit operation should be stopped immediately, and a maintenance team should be organized to carry out on-site fault diagnosis and repair to ensure that the equipment returns to normal operation.

Images