Wind driven generator state remote monitoring system based on Internet of Things

Abstract

The invention discloses a wind driven generator state remote monitoring system based on the Internet of Things, and relates to the technical field of wind power generation equipment monitoring, and the system comprises a sensing module, a transmission module, a remote processing module and a user terminal module. The sensing module is used for accurately collecting various physical parameters such as vibration, temperature, pressure and rotating speed during operation of the wind driven generator by using various sensors, so that the operation condition of equipment is comprehensively mastered, and a data basis is provided for subsequent analysis and processing; according to the method, intelligent prediction of the future operation state of the wind driven generator is realized through deep learning and time sequence analysis, the fault type and time possibly occurring to the equipment can be predicted based on historical data and real-time data, powerful support is provided for operation and maintenance decision making, an operation and maintenance team can prepare in advance, and the operation and maintenance efficiency is improved. And targeted maintenance measures are taken, so that the maintenance cost is reduced, and the operation efficiency and the safety of the equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation equipment monitoring, and in particular to a remote monitoring system for wind power generator status based on the Internet of Things. Background Art

[0002] As the wind power industry is developing rapidly, the operation and maintenance of wind turbines face many challenges. On the one hand, due to their wide distribution and remote and harsh environments, manual inspections are difficult, costly and inefficient. On the other hand, traditional monitoring methods are difficult to obtain real-time and comprehensive information on the operating status of equipment, and cannot respond in time when a fault occurs, resulting in extended downtime, serious power generation losses, and increased maintenance costs; and when the equipment does not show abnormal data, it is impossible to understand the status of the equipment, which is likely to cause greater losses.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that wind turbines are widely distributed and located in remote and harsh environments, where manual inspection is difficult, costly and inefficient, and traditional monitoring methods cannot understand the status in advance when there is no abnormal data in the equipment, which may cause greater losses. A remote monitoring system for wind turbine status based on the Internet of Things is proposed.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The remote monitoring system of wind turbine status based on the Internet of Things includes:

[0007] The perception module is used to collect various physical parameters of wind turbines during operation using a variety of sensors to understand the operating status of the equipment and provide a data basis for subsequent analysis and processing;

[0008] The transmission module is used to transmit the data collected by the sensing module through network communication to ensure that the data can be transmitted from the wind turbine to the remote processing module in a timely manner;

[0009] Remote processing module, used to store, analyze and calculate the transmitted data, mine the data value through big data analysis and intelligent algorithms, establish equipment operation model, compare normal and abnormal data, realize fault diagnosis and prediction functions, and provide a basis for operation and maintenance decision-making;

[0010] The user terminal module is used to provide users with an interactive interface to display the operating status, processing results and warning information of the wind turbine in real time, making it convenient for operation and maintenance personnel to grasp the equipment status anytime and anywhere, while supporting users to perform remote control operations and receive system feedback.

[0011] Furthermore, the operation process of the remote processing module is as follows:

[0012] When data arrives at the remote processing module from the transmission module, it first performs a data integrity and accuracy check to check whether the data frame is complete and whether there is data loss or garbled code. Each batch of data is verified through a cyclic redundancy check algorithm. If data errors are found, a retransmission request is sent to the transmission module to ensure that accurate and complete data is received.

[0013] Classify and store data according to its type and source, and use a distributed database architecture to quickly write real-time data into the corresponding database table. At the same time, establish data indexes for subsequent query and call data.

[0014] Conduct in-depth mining and analysis of stored historical data, use statistical analysis methods to calculate the mean, variance, and extreme value statistical indicators of various parameters, and analyze the parameter change range and rules of equipment in different time periods and different working conditions;

[0015] Combined with the real-time collected data for dynamic modeling, the machine learning algorithm of support vector machine or neural network algorithm is used to establish the operation status model of the wind turbine, and the real-time vibration, temperature, pressure, and speed parameter data are used as input variables. The output value of the equipment's operation status is predicted through model calculation, and the predicted value is compared and analyzed with the actual collected value to obtain the data deviation;

[0016] When data anomalies are found, fault feature extraction is performed using signal processing technology, including spectrum analysis of vibration signals through fast Fourier transform to extract abnormal frequency components; the mutation points and change slope features of temperature data are extracted, and the extracted features are matched and analyzed with known fault types by establishing a fault feature library;

[0017] Based on time series analysis and machine learning prediction models, the future operating status of the equipment is predicted. According to the current equipment operating parameter trend and the parameter change law before the historical failure, the probability of failure, the type and severity of the failure are predicted. By analyzing the rising trend of bearing temperature and the change of vibration frequency, the probability of bearing failure in the next few days is predicted, and early warning information is issued in advance;

[0018] When no data anomalies are found, the monitoring data of all wind turbines of the same model without abnormalities are collected to conduct abnormal analysis of parameter change trends.

[0019] Furthermore, the specific process of the remote processing module performing abnormal analysis of parameter change trends is as follows:

[0020] Collect monitoring data from wind turbines of the same model in different geographical locations and operating environments, clean and pre-process the collected data, remove noise and outlier interference factors, and ensure data quality;

[0021] Then, all operating parameter data are standardized, and a unified data format, unit and measurement basis are determined according to the design specifications and operating standards of wind turbines;

[0022] The data smoothing technology of moving average method or exponential smoothing method is used to process the time series data of the operating parameters of each wind turbine and extract the parameter change trend curve. For the vibration parameters, the change of vibration trend is displayed by calculating the moving average of the vibration amplitude; for the temperature parameters, the exponential smoothing method is used to process the change trend of temperature over time;

[0023] The dynamic time warping algorithm or similarity measurement method is used to compare the parameter trends of different wind turbines. The time warping algorithm is used to calculate the similarity between two time series curves. By calculating the distance or similarity index between the trend curves of the same parameter of different wind turbines, it is determined whether there is an anomaly.

[0024] According to historical data and expert experience, the normal range threshold of parameter change trend is set. The initial threshold is obtained through statistical analysis of parameter trends of fans of the same model under normal operation. At the same time, an adaptive learning algorithm is used to continuously adjust the threshold according to newly collected data so that the threshold accurately reflects the actual operating status of the equipment. When the difference between the parameter trend of a fan and the trend of other fans of the same model exceeds the threshold, it is judged as abnormal.

[0025] When no abnormality is determined, the comprehensive deviation values ​​of wind turbine parameters are analyzed through comprehensive evaluation parameters;

[0026] When an abnormality is confirmed, the early warning mechanism is immediately activated. The early warning information includes the identification of the abnormal fan, the type of abnormal parameter and the specific description of the abnormal trend. The early warning information is sent to the operation and maintenance personnel through various communication methods so that they can take timely measures for inspection and maintenance to avoid the occurrence or expansion of faults.

[0027] Furthermore, the specific operation steps of the remote processing module to analyze the comprehensive deviation value of the wind turbine parameters through the comprehensive evaluation parameters are as follows:

[0028] When no abnormality is determined, comprehensive evaluation parameters are determined. These parameters include physical parameters such as vibration, temperature, pressure, and speed collected from the sensing module. For each comprehensive evaluation parameter, a standard reference value is determined based on the design specifications of the wind turbine, technical information provided by the manufacturer, and statistical analysis of historical operating data.

[0029] According to the importance of the parameter, a weight value is set for each comprehensive evaluation parameter. For each comprehensive evaluation parameter, the deviation from the standard parameter is calculated. Specifically, the actual measurement value is subtracted from the standard reference value, and the absolute value is taken, that is, , through the formula: To obtain the comprehensive deviation value ZBZ, where ZBZ is the calculated comprehensive deviation value; n is the number of comprehensive parameters involved in the calculation, is the weight value of the i-th comprehensive evaluation parameter; are the actual measured value and standard reference value of the i-th comprehensive evaluation parameter respectively;

[0030] The calculated comprehensive deviation value is compared with the preset comprehensive deviation threshold; when the comprehensive deviation value is less than or equal to the comprehensive deviation threshold, it is judged that the current operating status of the equipment meets the standard; when the comprehensive deviation value is greater than the comprehensive deviation threshold, it is judged that there is an abnormality in the equipment operating status, and further analysis and processing are carried out.

[0031] Furthermore, the operation process of the perception module is as follows:

[0032] Determine the types of physical parameters that need to be collected based on the structural characteristics and monitoring requirements of the wind turbine; obtain the sensor's measurement range, accuracy, and response time performance indicators to determine whether the detection standards are met to ensure that it meets the requirements for wind turbine operating status monitoring;

[0033] Arrange sensors at the locations of wind turbines, including installing vibration sensors at the blade roots, gearboxes, and generator bearings to comprehensively monitor the vibration of mechanical components; install temperature sensors at the heating locations of generator windings and bearing seats to monitor temperature changes in real time;

[0034] Determine the installation and fixing methods of the sensor to ensure that the sensor works stably during the operation of the wind turbine and is not affected by external environmental factors;

[0035] According to the operating characteristics and monitoring requirements of wind turbines, determine the data collection frequency, analyze the pressure of data storage and transmission, and select the matching data collection frequency under the premise of ensuring monitoring accuracy;

[0036] Filter the collected raw data to remove noise and interference signals. Use digital filtering algorithms to select appropriate filtering methods based on the characteristics of different parameters.

[0037] Calibrate and normalize the data to ensure that the data collected by different sensors are comparable; identify and process abnormal data by setting thresholds or using statistical methods to identify data that deviates from the normal range, and take corresponding processing measures, including marking it as abnormal data and performing data interpolation.

[0038] Furthermore, the operation process of the transmission module is as follows:

[0039] The raw data collected from different sensors have various formats. First, these data are packaged in a predetermined unified format. Specifically, a structure data format including device identification, sensor type, acquisition timestamp, and data value fields is defined. For analog sensor data, analog-to-digital conversion is performed and then encoded according to the standard value range, including: mapping the temperature value in the range of -50°C to 150°C collected by the temperature sensor to an integer range of 0-65535, and encoding using the following formula: ;

[0040] The encapsulated data is grouped according to a certain size, and a cyclic redundancy check code is added to each group of data; the cyclic redundancy check is calculated using the following formula: CRC is a cyclic redundancy check code used to detect whether errors occur during data transmission; remainder represents the remainder; n is the polynomial order determined according to the data length and protocol requirements. is the polynomial corresponding to the original data, It is a pre-selected generating polynomial used to detect whether errors occur in data transmission at the receiving end;

[0041] Periodically detect the signal strength, bandwidth, and latency parameters of available network links, evaluate network latency by sending test packets and calculating the round-trip time, use the signal reception strength indicator to measure signal strength, and combine these parameters to evaluate the quality score of each link using a weighted algorithm. , where They are signal strength, bandwidth, and delay parameters, The preset weight coefficients are respectively the signal strength, bandwidth and delay parameters. The link with the highest quality score Q is selected as the current transmission channel. If the quality of the current link drops to the preset threshold, it will automatically switch to other backup links.

[0042] Furthermore, the operation process of the transmission module also includes:

[0043] Dynamically adjust the data transmission rate according to the real-time bandwidth of the network link and the priority of the data; use congestion control algorithms, including variants of the window-based TCP congestion control algorithm;

[0044] When the network bandwidth meets the standard, the transmission window size is gradually increased to increase the transmission rate; when network congestion or packet loss is detected, the transmission window size is reduced to reduce the transmission rate. The adjustment formula of the transmission window size is as follows: , where is the calculated transmission window size; is the adjustment coefficient, B is the available bandwidth information fed back by the network;

[0045] Before data transmission, the data is encrypted using an encryption algorithm. The Advanced Encryption Standard algorithm is used to encrypt the data in 128-bit blocks. The key is generated by combining the device's unique identification and timestamp information and performing a hash function operation to ensure the security and randomness of the key.

[0046] Adopt SSL / TLS transport layer protocol to establish encrypted channels for data transmission. When establishing a connection, perform certificate verification and key exchange operations to ensure that data is not stolen or tampered with during transmission. The encryption algorithm and key length parameters are negotiated through the handshake process to achieve end-to-end secure communication.

[0047] When the network is unstable or the transmission is interrupted, the local cache space is used to temporarily store the data that has not been successfully transmitted. The cached data is managed according to the first-in-first-out principle. When the cache space reaches the upper limit, the data is selectively deleted according to its importance and timeliness, and the latest collected data is retained first.

[0048] After the network connection is restored, the location of the last transmission interruption is automatically detected, and the data information that has been successfully received is obtained by interacting with the receiving end. The unfinished data is continued from the breakpoint to ensure the integrity of the data. The identification and sequence number information of the data block is used to achieve the accuracy of breakpoint resumption. After receiving the data, the receiving end verifies and confirms it and feeds back the transmission results to the sending end.

[0049] Furthermore, the operation process of the user terminal module is as follows:

[0050] Establish communication with the server, authenticate and obtain permissions when logging in, receive data messages and parse them according to format specifications, and convert binary or JSON / XML format data into a displayable format;

[0051] Display operation status information in charts, mark parameter ranges, automatically warn of abnormalities, and present the overall status on the home page. Navigate to view subsystem details, set a quick return button, support click and gesture operations, click to pop up details, and provide feedback prompts for operations;

[0052] Generate control instructions based on user operations, encrypt and encode them and send them to the server or controller to receive the instruction execution results. If successful, display prompts and update status. If failed, display reasons and record logs.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] (1) The present invention greatly improves the monitoring efficiency of the equipment by collecting key physical parameters of the wind turbine in real time and using a remote processing module for in-depth analysis. It can timely discover and warn of potential faults, thereby reducing the risk of unexpected downtime and enhancing the reliability of the wind turbine. This real-time monitoring and warning mechanism enables operation and maintenance personnel to respond quickly and take preventive maintenance measures, effectively avoiding power generation losses caused by equipment failures.

[0055] (2) The present invention adopts advanced data transmission and processing technology to ensure the accuracy and integrity of data during collection, transmission and processing. By using cyclic redundancy check and encryption algorithm, the security of data transmission is guaranteed, and the risk of data loss, garbled or tampering during transmission is prevented. In addition, the system can dynamically adjust the transmission strategy according to network conditions, optimize the data transmission efficiency, and ensure the timeliness and integrity of data.

[0056] (3) The present invention, through deep learning and time series analysis, realizes intelligent prediction of the future operating status of wind turbines. It can predict the type and time of possible equipment failures based on historical data and real-time data, providing strong support for operation and maintenance decisions, allowing the operation and maintenance team to prepare in advance and take targeted maintenance measures, thereby reducing maintenance costs and improving the operating efficiency and safety of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0058] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0059] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0061] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0062] like Figure 1 As shown, the remote monitoring system for wind turbine status based on the Internet of Things includes a sensing module, a transmission module, a remote processing module and a user terminal module;

[0063] The perception module is used to use a variety of sensors to accurately collect various physical parameters of wind turbines during operation, such as vibration, temperature, pressure, speed and other information, so as to fully understand the operating status of the equipment and provide a data basis for subsequent analysis and processing;

[0064] According to the structural characteristics and monitoring requirements of the wind turbine, determine the type of physical parameters that need to be collected. For example, for the blades of the wind turbine, it is necessary to monitor their vibration to determine whether there is structural damage, and select a vibration sensor; for the generator part, it is necessary to monitor the temperature to prevent overheating failure, and select a suitable temperature sensor; consider the sensor's measurement range, accuracy, and response time performance indicators to ensure that it can meet the requirements of wind turbine operating status monitoring; for example, for a high-speed rotating main shaft, it is necessary to select a speed sensor with a short response time and high measurement accuracy to accurately capture the speed changes of the main shaft;

[0065] Arrange sensors rationally at key locations of wind turbines. For example, install vibration sensors at blade roots, gearboxes, generator bearings, etc. to comprehensively monitor the vibration of mechanical components. Install temperature sensors at generator windings, bearing seats, and other locations prone to heat to monitor temperature changes in real time. Determine the installation and fixing methods of sensors to ensure that the sensors can work stably during the operation of wind turbines and are not affected by external environmental factors. Determine the appropriate data acquisition frequency based on the operating characteristics and monitoring requirements of wind turbines. For rapidly changing parameters, such as vibration and speed, a higher acquisition frequency can be used, such as several times per second or even higher. For relatively stable parameters, such as temperature and pressure, a lower acquisition frequency can be used, such as once per minute. Considering the pressure of data storage and transmission, the data acquisition frequency should be reasonably selected on the premise of ensuring monitoring accuracy to avoid storage and transmission difficulties caused by excessive data volume.

[0066] Filter the collected raw data to remove noise and interference signals. Digital filtering algorithms such as low-pass filtering, high-pass filtering, band-pass filtering, etc. can be used to select appropriate filtering methods according to the characteristics of different parameters. For example, for vibration signals, band-pass filtering can be used to remove low-frequency environmental vibrations and high-frequency electromagnetic interference; calibrate and normalize the data to ensure that the data collected by different sensors are comparable; identify and process abnormal data, identify data that obviously deviates from the normal range by setting thresholds or using statistical methods, and take corresponding processing measures, including marking as abnormal data and performing data interpolation.

[0067] The transmission module is used to transmit the data collected by the sensing module stably, efficiently and safely through network communication, ensuring that the data can be transmitted from the wind turbine to the remote processing module in a timely manner, overcoming the limitations of distance and environmental factors;

[0068] The raw data collected from different sensors have various formats. First, these data are packaged in a predetermined unified format. For example, a structure data format containing fields such as device identification, sensor type, acquisition timestamp, and data value is defined. For analog sensor data, after analog-to-digital conversion, it is encoded according to the standard numerical range. For example, the temperature values ​​collected by the temperature sensor in the range of -50℃ to 150℃ are mapped to the integer range of 0-65535 and encoded using the following formula: ;

[0069] The encapsulated data is grouped according to a certain size, and a cyclic redundancy check (CRC) code is added to each group of data; the CRC is calculated using the following formula: CRC is a cyclic redundancy check code used to detect whether errors occur during data transmission; remainder represents the remainder; n is the polynomial order determined according to the data length and protocol requirements. is the polynomial corresponding to the original data, It is a pre-selected generating polynomial used to detect whether errors occur in data transmission at the receiving end;

[0070] Periodically detect the signal strength, bandwidth, and latency parameters of available network links, evaluate network latency by sending test packets and calculating the round-trip time (RTT), and use the received signal strength indication (RSSI) to measure signal strength. Combine these parameters and use a weighted algorithm to evaluate the quality score of each link. , where They are signal strength, bandwidth, and delay parameters, The preset weight coefficients of signal strength, bandwidth, and delay parameters are respectively selected, and the link with the highest quality score Q is selected as the current transmission channel. If the quality of the current link drops to a certain threshold, it will automatically switch to other backup links;

[0071] The data transmission rate is adjusted dynamically according to the real-time bandwidth of the network link and the priority of the data. A congestion control algorithm is used, such as a variant of the window-based TCP congestion control algorithm. When the network bandwidth is sufficient, the transmission window size is gradually increased to increase the transmission rate; when network congestion or packet loss is detected, the transmission window size is reduced to reduce the transmission rate. The adjustment formula of the transmission window size is as follows: , where is the calculated transmission window size; is the adjustment coefficient, B is the available bandwidth information fed back by the network; before data transmission, the data is encrypted using an encryption algorithm, and the Advanced Encryption Standard (AES) algorithm is used to encrypt the data in 128-bit blocks. The key is generated by combining the device's unique identification and timestamp information and is obtained through a hash function operation to ensure the security and randomness of the key; a secure transport layer protocol, including the SSL / TLS protocol, is used to establish an encrypted channel for data transmission. When establishing a connection, certificate verification and key exchange are performed to ensure that the data is not stolen or tampered with during transmission. The encryption algorithm and key length parameters are negotiated through a handshake process to achieve end-to-end secure communication; when the network When instability or transmission interruption occurs, the local cache space is used to temporarily store data that has not been successfully transmitted. The cached data is managed according to the first-in-first-out (FIFO) principle. When the cache space reaches a certain upper limit, the data is selectively deleted according to its importance and timeliness, with priority given to retaining key data and the latest collected data. After the network connection is restored, the location of the last transmission interruption is automatically detected, and the data information that has been successfully received is obtained through interaction with the receiving end. The unfinished data is continued to be transmitted from the breakpoint to ensure data integrity. The identification and sequence number information of the data block is used to achieve the accuracy of breakpoint resumption. After receiving the data, the receiving end verifies and confirms it and feeds back the transmission result to the sending end.

[0072] The remote processing module is used to store, analyze, and calculate the transmitted data. It mines the data value through big data analysis and intelligent algorithms, establishes equipment operation models, compares normal and abnormal data, and implements fault diagnosis and prediction functions to provide a basis for operation and maintenance decisions.

[0073] When the data arrives at the remote processing module from the transmission module, the data integrity and accuracy are first checked to check whether the data frame is complete and whether there is data loss or garbled code. Each batch of data is verified through the cyclic redundancy check (CRC) algorithm. When the data is found to be incorrect, a request for retransmission is sent to the transmission module to ensure that accurate and complete data is received; the data is classified and stored according to the type (such as vibration data, temperature data, etc.) and source (corresponding wind turbine number, sensor number), and a distributed database architecture is used to quickly write real-time data into the corresponding database table. At the same time, a data index is established so that the data can be quickly queried and called later to improve data processing efficiency;

[0074] Conduct in-depth mining and analysis on a large amount of stored historical data, use statistical analysis methods to calculate the mean, variance, and extreme value statistical indicators of various parameters, and analyze the parameter change range and rules of the equipment under different time periods and different working conditions. For example, analyze the temperature change trend of wind turbines in different seasons and different wind speeds to provide a reference for judging whether the current temperature data is abnormal; conduct dynamic modeling based on real-time collected data, use machine learning algorithms such as support vector machines (SVM) or neural network algorithms to establish an operating status model for wind turbines, and use real-time vibration, temperature, pressure, speed and other multi-parameter data as input variables. Use the model to calculate and predict the output value of the equipment's operating status, compare and analyze the predicted value with the actual collected value, and obtain data deviation;

[0075] When data anomalies are found, fault feature extraction is performed, and signal processing technology, such as fast Fourier transform (FFT), is used to perform spectrum analysis on the vibration signal to extract abnormal frequency components; the mutation point, change slope and other features of the temperature data are extracted, and the extracted features are matched and analyzed with known fault types by establishing a fault feature library; based on time series analysis and machine learning prediction models, the future operating status of the equipment is predicted, and the probability of failure in the future, as well as the type and severity of the failure are predicted based on the current equipment operating parameter trend and the parameter change law before the historical failure. For example, by analyzing the rising trend of the bearing temperature and the change of the vibration frequency, it is predicted that the bearing may fail in the next few days, and early warning information is issued in advance;

[0076] When no data anomalies are found, the monitoring data of all wind turbines of the same model without abnormalities are collected to analyze the abnormal trend of parameter changes. The specific process is as follows:

[0077] Monitoring data is collected from wind turbines of the same model in different geographical locations and operating environments. The collected data is cleaned and preprocessed to remove noise and outlier interference factors to ensure data quality. In order to facilitate comparison, all operating parameter data are standardized. According to the design specifications and operating standards of wind turbines, a unified data format, unit and measurement benchmark are determined. For example, temperature data is unified as degrees Celsius, speed data is unified as revolutions per minute, etc., to ensure that data from different data sources are comparable. The moving average method or exponential smoothing method is used to process the time series data of the operating parameters of each wind turbine to extract the trend of parameter changes. Trend curves, where for vibration parameters, the moving average of the vibration amplitude is calculated to show the change of vibration trend; for temperature parameters, the exponential smoothing method is used to process the change trend of temperature over time, so that it can more clearly reflect the long-term trend and short-term fluctuations; the dynamic time warping (DTW) algorithm or similarity measurement method is used to compare the parameter trends of different wind turbines. The DTW algorithm can effectively calculate the similarity between two time series curves, even if they are not completely synchronized on the time axis or there is a certain phase difference, it can also measure their similarity; by calculating the distance or similarity index between the trend curves of the same parameter of different wind turbines, it is judged whether there is an abnormality;

[0078] Based on historical data and expert experience, the normal range threshold of the parameter change trend is set. The initial threshold is obtained through statistical analysis of the parameter trends of a large number of fans of the same model under normal operating conditions. At the same time, an adaptive learning algorithm is used to continuously adjust the threshold based on the newly collected data to make it more accurately reflect the actual operating conditions of the equipment. When the parameter trend of a fan differs from that of most other fans of the same model by more than the threshold, it is judged to be abnormal.

[0079] When no abnormality is determined, the parameters that need to be comprehensively evaluated are determined. These parameters include physical parameters such as vibration, temperature, pressure, and speed collected from the sensing module. For each comprehensive evaluation parameter, its standard reference value is determined based on the design specifications of the wind turbine, the technical information provided by the manufacturer, and the statistical analysis of historical operating data. For example, for a certain type of wind turbine under normal operating conditions, the standard value of the bearing temperature is between 40°C and 60°C, and the standard value of the vibration amplitude is a certain value within a specific frequency range. A weight value is set for each comprehensive evaluation parameter according to the importance of the parameter. For each comprehensive evaluation parameter, its deviation from the standard parameter is calculated. Specifically, the actual measured value is subtracted from the standard reference value, and the absolute value is taken, that is, , through the formula: To obtain the comprehensive deviation value ZBZ, where n is the number of comprehensive parameters involved in the calculation, is the weight value of the i-th comprehensive evaluation parameter, and the weight value is 1; represent the actual measured value and standard reference value of the i-th comprehensive evaluation parameter respectively.

[0080] The calculated comprehensive deviation value is compared with the preset comprehensive deviation threshold. The comprehensive deviation threshold is a critical value determined based on historical data and experience to judge whether the equipment operating status meets the standard. When the comprehensive deviation value is less than or equal to the comprehensive deviation threshold, it is considered that the current operating status of the equipment meets the standard. When the comprehensive deviation value is greater than the comprehensive deviation threshold, it indicates that the equipment operating status may be abnormal and requires further analysis and processing.

[0081] When an abnormality is confirmed, the early warning mechanism is immediately activated. The early warning information includes the identification of the abnormal fan, the type of abnormal parameter, and the specific description of the abnormal trend. The early warning information is sent to the operation and maintenance personnel through various communication methods (such as SMS, email, system pop-up windows, etc.) so that timely measures can be taken to conduct inspections and repairs to avoid the occurrence or expansion of faults.

[0082] The user terminal module is used to provide users with an intuitive and convenient interactive interface, which displays the operating status, processing results and warning information of wind turbines in real time, making it convenient for operation and maintenance personnel to grasp the equipment status anytime and anywhere, and supports users to perform remote control operations and receive system feedback;

[0083] Establish communication with the server (such as using TCP / IP or WebSocket protocol), authenticate and obtain permissions when logging in, receive data messages and parse them according to format specifications, and convert binary or JSON / XML format data into a displayable format; display operation status information in charts (waveforms, bars, broken lines, etc.), mark key parameter ranges, automatically warn of abnormalities, present overall status on the home page, navigate to view subsystem details, set quick return buttons, support clicks, gestures, etc., click to pop up details, and have feedback prompts for operations; generate control instructions based on user operations, encrypt and encode them and send them to the server or controller, receive the results of instruction execution, display prompts and update status if successful, display reasons for failure and record logs.

[0084] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Remote monitoring system of wind turbine status based on Internet of Things, It is characterized in that include: The perception module is used to collect various physical parameters of wind turbines during operation using a variety of sensors to understand the operating status of the equipment and provide a data basis for subsequent analysis and processing; The transmission module is used to transmit the data collected by the sensing module through network communication to ensure that the data can be transmitted from the wind turbine to the remote processing module in a timely manner; Remote processing module, used to store, analyze and calculate the transmitted data, mine the data value through big data analysis and intelligent algorithms, establish equipment operation model, compare normal and abnormal data, realize fault diagnosis and prediction functions, and provide a basis for operation and maintenance decision-making; The user terminal module is used to provide users with an interactive interface to display the operating status, processing results and warning information of the wind turbine in real time, making it convenient for operation and maintenance personnel to grasp the equipment status anytime and anywhere, while supporting users to perform remote control operations and receive system feedback.

2. According to the remote monitoring system for wind turbine status based on the Internet of Things in claim 1, It is characterized in that The operation process of the remote processing module is as follows: When data arrives at the remote processing module from the transmission module, it first performs a data integrity and accuracy check to check whether the data frame is complete and whether there is data loss or garbled code. Each batch of data is verified through a cyclic redundancy check algorithm. If data errors are found, a retransmission request is sent to the transmission module to ensure that accurate and complete data is received. Classify and store data according to its type and source, and use a distributed database architecture to quickly write real-time data into the corresponding database table. At the same time, establish data indexes for subsequent query and call data. Conduct in-depth mining and analysis of stored historical data, use statistical analysis methods to calculate the mean, variance, and extreme value statistical indicators of various parameters, and analyze the parameter change range and rules of equipment in different time periods and different working conditions; Combined with the real-time collected data for dynamic modeling, the machine learning algorithm of support vector machine or neural network algorithm is used to establish the operation status model of the wind turbine, and the real-time vibration, temperature, pressure, and speed parameter data are used as input variables. The output value of the equipment's operation status is predicted through model calculation, and the predicted value is compared and analyzed with the actual collected value to obtain the data deviation; When data anomalies are found, fault feature extraction is performed using signal processing technology, including spectrum analysis of vibration signals through fast Fourier transform to extract abnormal frequency components; the mutation points and change slope features of temperature data are extracted, and the extracted features are matched and analyzed with known fault types by establishing a fault feature library; Based on time series analysis and machine learning prediction models, the future operating status of the equipment is predicted. According to the current equipment operating parameter trend and the parameter change law before the historical failure, the probability of failure, the type and severity of the failure are predicted. By analyzing the rising trend of bearing temperature and the change of vibration frequency, the probability of bearing failure in the next few days is predicted, and early warning information is issued in advance; When no data anomalies are found, the monitoring data of all wind turbines of the same model without abnormalities are collected to conduct abnormal analysis of parameter change trends.

3. According to the remote monitoring system for wind turbine status based on the Internet of Things in claim 2, It is characterized in that The specific process of the remote processing module performing abnormal analysis of parameter change trends is as follows: Collect monitoring data from wind turbines of the same model in different geographical locations and operating environments, clean and pre-process the collected data, remove noise and outlier interference factors, and ensure data quality; Then, all operating parameter data are standardized, and a unified data format, unit and measurement basis are determined according to the design specifications and operating standards of wind turbines; The data smoothing technology of moving average method or exponential smoothing method is used to process the time series data of the operating parameters of each wind turbine and extract the parameter change trend curve. For the vibration parameters, the change of vibration trend is displayed by calculating the moving average of the vibration amplitude; for the temperature parameters, the exponential smoothing method is used to process the change trend of temperature over time; The dynamic time warping algorithm or similarity measurement method is used to compare the parameter trends of different wind turbines. The time warping algorithm is used to calculate the similarity between two time series curves. By calculating the distance or similarity index between the trend curves of the same parameter of different wind turbines, it is determined whether there is an anomaly. According to historical data and expert experience, the normal range threshold of parameter change trend is set. The initial threshold is obtained through statistical analysis of parameter trends of fans of the same model under normal operation. At the same time, an adaptive learning algorithm is used to continuously adjust the threshold according to newly collected data so that the threshold accurately reflects the actual operating status of the equipment. When the difference between the parameter trend of a fan and the trend of other fans of the same model exceeds the threshold, it is judged as abnormal. When no abnormality is determined, the comprehensive deviation values ​​of wind turbine parameters are analyzed through comprehensive evaluation parameters; When an abnormality is confirmed, the early warning mechanism is immediately activated. The early warning information includes the identification of the abnormal fan, the type of abnormal parameter and the specific description of the abnormal trend. The early warning information is sent to the operation and maintenance personnel through various communication methods so that they can take timely measures for inspection and maintenance to avoid the occurrence or expansion of faults.

4. According to claim 3, the remote monitoring system for wind turbine status based on the Internet of Things, It is characterized in that The specific operation steps of the remote processing module to analyze the comprehensive deviation value of the wind turbine parameters through the comprehensive evaluation parameters are as follows: When no abnormality is determined, comprehensive evaluation parameters are determined. These parameters include physical parameters such as vibration, temperature, pressure, and speed collected from the sensing module. For each comprehensive evaluation parameter, a standard reference value is determined based on the design specifications of the wind turbine, technical information provided by the manufacturer, and statistical analysis of historical operating data. According to the importance of the parameter, a weight value is set for each comprehensive evaluation parameter. For each comprehensive evaluation parameter, the deviation from the standard parameter is calculated. Specifically, the actual measurement value is subtracted from the standard reference value, and the absolute value is taken, that is, , through the formula: , to obtain the comprehensive deviation value ZBZ, where ZBZ is the calculated comprehensive deviation value; n is the number of comprehensive parameters involved in the calculation, is the weight value of the i-th comprehensive evaluation parameter; are the actual measured value and standard reference value of the i-th comprehensive evaluation parameter respectively; Comparing the calculated comprehensive deviation value with a preset comprehensive deviation threshold; When the comprehensive deviation value is less than or equal to the comprehensive deviation threshold, it is judged that the current operating status of the equipment meets the standard; When the comprehensive deviation value is greater than the comprehensive deviation threshold, it is judged that the equipment operation status is abnormal, and further analysis and processing are performed.

5. According to the remote monitoring system for wind turbine status based on the Internet of Things in claim 1, It is characterized in that The operation process of the perception module is as follows: Determine the types of physical parameters that need to be collected based on the structural characteristics and monitoring requirements of the wind turbine; obtain the sensor's measurement range, accuracy, and response time performance indicators to determine whether the detection standards are met to ensure that it meets the requirements for wind turbine operating status monitoring; Arrange sensors at the locations of wind turbines, including installing vibration sensors at the blade roots, gearboxes, and generator bearings to comprehensively monitor the vibration of mechanical components; install temperature sensors at the heating locations of generator windings and bearing seats to monitor temperature changes in real time; Determine the installation and fixing methods of the sensor to ensure that the sensor works stably during the operation of the wind turbine and is not affected by external environmental factors; According to the operating characteristics and monitoring requirements of wind turbines, determine the data collection frequency, analyze the pressure of data storage and transmission, and select the matching data collection frequency under the premise of ensuring monitoring accuracy; Filter the collected raw data to remove noise and interference signals. By using digital filtering algorithms, select the corresponding filtering method according to the characteristics of different parameters. Calibrate and normalize the data to ensure that the data collected by different sensors are comparable; identify and process abnormal data by setting thresholds or using statistical methods to identify data that deviates from the normal range, and take corresponding processing measures, including marking it as abnormal data and performing data interpolation.

6. The remote monitoring system for wind turbine status based on the Internet of Things according to claim 1, It is characterized in that The operation process of the transmission module is as follows: The raw data collected from different sensors have various formats. First, these data are packaged in a predetermined unified format. Specifically, a structure data format including device identification, sensor type, acquisition timestamp, and data value fields is defined. For analog sensor data, analog-to-digital conversion is performed and then encoded according to the standard value range, including: mapping the temperature value in the range of -50°C to 150°C collected by the temperature sensor to an integer range of 0-65535, and encoding using the following formula: ; The encapsulated data is grouped according to the preset size, and a cyclic redundancy check code is added to each group of data; the cyclic redundancy check is calculated using the following formula: CRC is a cyclic redundancy check code used to detect whether errors occur during data transmission; remainder represents the remainder; n is the polynomial order determined according to the data length and protocol requirements. is the polynomial corresponding to the original data, It is a pre-selected generating polynomial used to detect whether errors occur in data transmission at the receiving end; Periodically detect the signal strength, bandwidth, and latency parameters of available network links, evaluate network latency by sending test packets and calculating the round-trip time, use the signal reception strength indicator to measure signal strength, and combine these parameters to evaluate the quality score of each link using a weighted algorithm. , where They are signal strength, bandwidth, and delay parameters, The preset weight coefficients are respectively the signal strength, bandwidth and delay parameters. The link with the highest quality score Q is selected as the current transmission channel. If the quality of the current link drops to the preset threshold, it will automatically switch to other backup links.

7. The remote monitoring system for wind turbine status based on the Internet of Things according to claim 6, It is characterized in that The operation process of the transmission module also includes: Dynamically adjust the data transmission rate according to the real-time bandwidth of the network link and the priority of the data; use congestion control algorithms, including variants of the window-based TCP congestion control algorithm; When the network bandwidth meets the standard, the transmission window size is gradually increased to increase the transmission rate; when network congestion or packet loss is detected, the transmission window size is reduced to reduce the transmission rate. The adjustment formula of the transmission window size is as follows: , where is the calculated transmission window size; is the adjustment coefficient, B is the available bandwidth information fed back by the network; Before data transmission, the data is encrypted using an encryption algorithm. The Advanced Encryption Standard algorithm is used to encrypt the data in 128-bit blocks. The key is generated by combining the device's unique identification and timestamp information and performing a hash function operation to ensure the security and randomness of the key. Adopt SSL / TLS transport layer protocol to establish encrypted channels for data transmission. When establishing a connection, perform certificate verification and key exchange operations to ensure that data is not stolen or tampered with during transmission. The encryption algorithm and key length parameters are negotiated through the handshake process to achieve end-to-end secure communication. When the network is unstable or the transmission is interrupted, the local cache space is used to temporarily store the data that has not been successfully transmitted. The cached data is managed according to the first-in-first-out principle. When the cache space reaches the upper limit, the data is selectively deleted according to its importance and timeliness, and the latest collected data is retained first. After the network connection is restored, the location of the last transmission interruption is automatically detected, and the data information that has been successfully received is obtained by interacting with the receiving end. The unfinished data is continued from the breakpoint to ensure the integrity of the data. The identification and sequence number information of the data block is used to achieve the accuracy of breakpoint resumption. After receiving the data, the receiving end verifies and confirms it and feeds back the transmission results to the sending end.

8. The remote monitoring system for wind turbine status based on the Internet of Things according to claim 1, It is characterized in that The operation process of the user terminal module is as follows: Establish communication with the server, authenticate and obtain permissions when logging in, receive data messages and parse them according to format specifications, and convert binary or JSON / XML format data into display format; Display operation status information in charts, mark parameter ranges, automatically warn of abnormalities, and present the overall status on the home page. Navigate to view subsystem details, set a quick return button, support click and gesture operations, click to pop up details, and provide feedback prompts for operations; Generate control instructions based on user operations, encrypt and encode them and send them to the server or controller to receive the instruction execution results. If successful, display prompts and update status. If failed, display reasons and record logs.

Images