Comprehensive monitoring system for running state of fan and noise and current detection method thereof

Abstract

The invention relates to the technical field of industrial monitoring, in particular to a fan running state comprehensive monitoring system and a noise and current detection method thereof, and the system comprises a noise data acquisition module, a vibration noise correlation analysis module, a running current acquisition module, an abnormal current detection module, an equipment fault diagnosis module and a performance degradation prediction module. According to the method, the sound data are collected, the frequency and amplitude changes are analyzed, the types of various sound sources are recognized, abnormity caused by mechanical parts is found in the early stage, association analysis of vibration data and sound data is combined, understanding of the physical state of the fan is enhanced, and by monitoring current data and the fan blade rotating speed in real time, the fan blade rotating speed can be accurately detected. Abnormal detection of the current data and evaluation of the current stability are realized, a data basis is provided for fault diagnosis, the operation efficiency and the performance degradation trend of the fan are evaluated in combination with the current data, the service life and the maintenance period of equipment are effectively predicted, and the operation strategy and the maintenance plan of the fan are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial monitoring, and in particular to a comprehensive monitoring system for the operation status of a fan and a noise and current detection method thereof. Background Art

[0002] The field of industrial monitoring technology focuses on using a variety of sensors, control systems and data analysis tools to monitor and manage industrial production processes, improve the efficiency, reliability and safety of industrial systems, monitor equipment performance and production efficiency through real-time data collection, including temperature, pressure, flow, vibration, and use a variety of data analysis algorithms and machine learning technologies to improve the ability to parse complex data patterns, support decision-making and preventive maintenance strategies, and combine real-time fault detection, performance evaluation and predictive maintenance to identify and solve potential problems in advance, reduce downtime, extend equipment life, and optimize resource utilization.

[0003] Among them, the comprehensive monitoring system for fan operation status focuses on evaluating and maintaining fan performance. Through an integrated sensor network, it collects noise and current data generated by the fan during operation, analyzes the operating status of the fan, identifies performance degradation and signs of failure, and reduces the occurrence of failures through predictive maintenance. It improves the operating efficiency of the fan and extends its service life, ensures continuous and safe operation, reduces maintenance costs, optimizes the maintenance plan and operation strategy of the fan, ensures the continuous and stable operation of the system, and improves overall production efficiency.

[0004] Traditional fan operating status monitoring technology has limitations in processing complex data patterns and providing real-time fault detection. It cannot fully analyze and utilize the correlation between vibration and noise data, resulting in insufficiently timely or accurate identification of abnormal equipment conditions, delayed fault diagnosis, increased unplanned downtime, high maintenance costs and reduced production efficiency. It has limited capabilities in current anomaly detection and multivariate data analysis, making it difficult to evaluate fan performance under a variety of operating conditions, limiting the implementation of predictive maintenance strategies, failing to maximize equipment life and optimize resource utilization, and affecting the safety and stability of a variety of equipment operations in an industrial environment that deals with real-time changes. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a comprehensive monitoring system for the operation status of a fan and a noise and current detection method thereof.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, the comprehensive monitoring system for the operation status of the fan comprises: The noise data acquisition module is based on the sound acquisition equipment, collects the sound of the fan operation, analyzes the frequency and amplitude of the sound wave, identifies and classifies the various sounds generated by the fan operation, and obtains the sound signal classification results; The vibration noise correlation analysis module collects and records the vibration data of the fan in real time based on the sound signal classification result, uses the vibration sensor, analyzes the correlation between the vibration signal and the sound signal, and generates a correlation calculation result; The operating current acquisition module collects the current data and the fan blade speed in real time when the fan is running based on the calculation result of the mutual relationship, analyzes the change mode of the current under various speed conditions, and generates a current mode analysis result; The abnormal current detection module analyzes the current data based on the current mode analysis result, detects abnormal fluctuations in the current data, evaluates the stability of the current when the fan is running, and establishes current stability evaluation information.

[0007] The equipment fault diagnosis module identifies the type of fault based on the current stability evaluation information by comparing the current and sound signal patterns with a plurality of known fault modes, and generates a fan fault identification result; The performance degradation prediction module uses the fan fault identification result to calculate the fan operation efficiency according to the fan current data at various speeds, evaluates the fan performance degradation trend, predicts the fan service life, and obtains the fan operation monitoring record.

[0008] As a further scheme of the present invention, the sound signal classification results include motor operation sound characteristic information, fan blade impact sound characteristic information, and bearing abnormal sound characteristic information; the correlation calculation results include vibration and noise intensity correlation information, frequency distribution matching data, and correlation coefficient; the current pattern analysis results include current intensity change patterns under multiple speeds, current peak mark data sets, and fan blade speed and current relationship curves; the current stability evaluation information includes the frequency and intensity of current fluctuations, abnormal current event statistics, and current stability rating scores; the fan fault identification results include bearing damage diagnosis data, motor overheating signal characteristics, and fault type classification results; the fan operation monitoring records include fan efficiency evaluation data, performance degradation trend analysis results, and equipment predicted service life.

[0009] As a further solution of the present invention, the noise data acquisition module includes: The sound signal acquisition submodule is based on the sound acquisition device, which collects the sound of the fan in real time and converts it into digital signals to generate digital sound data; The sound wave analysis submodule is run to analyze the frequency and amplitude changes of the sound wave data based on the digitized sound data to obtain sound wave characteristic data; The operation sound classification submodule identifies and classifies various sounds generated by the operation of the fan, including motor operation sound, fan blade impact sound, and bearing abnormal sound, based on the acoustic wave characteristic data, and generates a sound signal classification result.

[0010] As a further solution of the present invention, the vibration noise correlation analysis module includes: The fan vibration monitoring submodule uses a vibration sensor to collect and record the vibration data of the fan in real time based on the sound signal classification result, and generates a vibration data record; The vibration signal analysis submodule analyzes the frequency distribution and intensity change of the vibration signal based on the vibration data record, extracts the key frequency and amplitude characteristics of the vibration signal, and obtains vibration characteristic data; The correlation analysis submodule analyzes the correlation between the sound signal and the vibration data based on the vibration characteristic data, calculates the correlation coefficient between the vibration and the noise by comparing the intensity and frequency distribution at the same time point, and generates a correlation analysis result.

[0011] As a further solution of the present invention, the specific formula for calculating the correlation coefficient between vibration and noise is:

[0012] in, Represents the correlation coefficient, which shows the strength of the relationship between vibration data and sound data. represents the total number of data points, indicating the total number of time points considered in the analysis, Represents a specific sequence number, used to indicate the position in the entire data set. Represents vibration data at a point in time The strength of Represents the sound signal at the same time point The strength of Represents the average intensity of vibration data, Represents the average intensity of the sound data.

[0013] As a further solution of the present invention, the operating current acquisition module includes: The operation status monitoring submodule monitors and records the current data and the fan blade speed when the fan is running in real time based on the mutual relationship analysis result to obtain the current and speed data; The operation characteristic analysis submodule analyzes the current change under various speed conditions based on the current and speed data, identifies the current characteristics under various speed conditions, and generates synchronous current analysis results; The operation mode analysis submodule analyzes the change mode of the current waveform under various working conditions based on the synchronous current analysis result, identifies the normal current fluctuation mode, sets the abnormal current detection threshold, and generates the current mode analysis result.

[0014] As a further solution of the present invention, the abnormal current detection module includes: The abnormal data extraction submodule identifies the unconventional fluctuations in the current data based on the current pattern analysis result by comparing it with the abnormal current detection threshold, records the abnormal intensity and frequency, and generates abnormal current data records; The abnormal mode analysis submodule analyzes the mode and conditions of the abnormal current based on the abnormal current data record, identifies the cause of the abnormal current, including motor overload, short circuit, power supply fluctuation, poor contact, and obtains the abnormal current analysis result; The stability real-time calculation submodule evaluates the stability of the current when the wind turbine is running in real time based on the current anomaly analysis result to obtain current stability evaluation information.

[0015] As a further solution of the present invention, the equipment fault diagnosis module includes: The abnormal event recording submodule analyzes the abnormal patterns of the current and sound data based on the current stability evaluation result, including the time and intensity of the abnormality, records the occurrence time of the abnormal event and the corresponding sound data, and obtains an abnormal event data set; The similarity calculation submodule calculates the similarity between the abnormal sound signal and the current data and a plurality of fault modes based on the abnormal event data set and using the sound and current data of the known fault modes to obtain a fault mode comparison record; The diagnosis result generation submodule identifies the fault type of the fan based on the fault mode comparison record, including bearing damage and motor overheating, and records the time information of the fault occurrence to generate a fan fault identification result.

[0016] As a further solution of the present invention, the performance degradation prediction module includes: The operation efficiency calculation submodule uses the fan fault identification result and the current data under various fan speeds to analyze and record the operation efficiency of the fan and generate efficiency analysis data; The decay rate calculation submodule evaluates the performance degradation trend of the fan through time series analysis based on the efficiency analysis data, including analyzing the speed of performance decay and generating performance degradation trend information; The operating life prediction submodule predicts the expected life of the fan based on the performance degradation trend information, predicts the maintenance cycle and adjusts the maintenance schedule in combination with the failure frequency of the fan, and generates a fan operation monitoring record.

[0017] A noise and current detection method is implemented based on the above-mentioned wind turbine operation status comprehensive monitoring system, and includes the following steps: S1: Based on the sound collection equipment, the sound signals of the fan in operation are collected in real time, and the frequency and amplitude of the signals are analyzed to extract key sound features, identify and classify the various sounds generated by the fan operation, and generate sound signal classification results; S2: Based on the sound signal classification result, collecting vibration data, analyzing the time synchronization and frequency similarity of the sound and vibration data, and calculating the correlation coefficient to generate a mutual relationship calculation result; S3: Based on the calculation result of the mutual relationship, the current data is monitored in real time and the fan blade speed is recorded, the change of the current waveform under various speeds is analyzed, the regular characteristics of the current change are identified, and the current pattern analysis result is generated; S4: Based on the current pattern analysis result, analyze the current data, identify and record abnormal fluctuations in the current, including peak intensity and abnormal frequency, evaluate the stability of the operating current, and establish current stability evaluation information; S5: Based on the current stability assessment information, the fault type is identified by comparing with the current and sound signal patterns of known fault modes, and the current data of the fan at various speeds is used to calculate the fan operating efficiency and evaluate the performance degradation trend, thereby generating a fan operation monitoring record.

[0018] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by collecting sound data and analyzing the frequency and amplitude changes, the types of various sound sources are identified, and anomalies caused by mechanical components are discovered at an early stage. The correlation analysis of vibration data and sound data is combined to enhance the understanding of the physical state of the fan. By real-time monitoring of current data and fan blade speed, anomaly detection of current data and evaluation of current stability are achieved, providing a data basis for fault diagnosis. The operating efficiency and performance degradation trend of the fan are evaluated in combination with current data, the service life and maintenance cycle of the equipment are effectively predicted, and the operation strategy and maintenance plan of the fan are optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a system flow chart of the present invention; Figure 2 It is a schematic diagram of the system framework of the present invention; Figure 3 It is a flow chart of the noise data acquisition module of the present invention; Figure 4 It is a flow chart of the vibration noise correlation analysis module of the present invention; Figure 5 This is a flow chart of the operating current acquisition module of the present invention; Figure 6 This is a flow chart of the abnormal current detection module of the present invention; Figure 7 It is a flow chart of the equipment fault diagnosis module of the present invention; Figure 8 is a flow chart of the performance degradation prediction module of the present invention; Fig. 9 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0022] See also Figure 1 to Figure 2 The present invention provides a technical solution, the comprehensive monitoring system for the operation status of a fan comprises: The noise data acquisition module is based on the sound acquisition equipment, collects the sound of the fan operation, analyzes the frequency and amplitude of the sound wave, identifies and classifies the various sounds generated by the fan operation, and obtains the sound signal classification results; The vibration noise correlation analysis module uses vibration sensors to collect and record the vibration data of the fan in real time based on the sound signal classification results, analyzes the correlation between the vibration signal and the sound signal, and generates the correlation calculation results; The operating current acquisition module collects the current data and fan blade speed in real time based on the calculation results of the mutual relationship, analyzes the change pattern of the current under various speed conditions, and generates the current pattern analysis results; The abnormal current detection module is based on the current pattern analysis results. By analyzing the current data, it detects abnormal fluctuations in the current data, evaluates the stability of the current when the fan is running, and establishes current stability evaluation information.

[0023] The equipment fault diagnosis module, based on the current stability assessment information, identifies the type of fault by comparing the current and sound signal patterns with a variety of known fault modes, and generates a fan fault identification result; The performance degradation prediction module uses the fan fault identification results to calculate the fan's operating efficiency based on the fan's current data at various speeds, evaluates the fan's performance degradation trend, predicts the fan's service life, and obtains the fan operation monitoring record.

[0024] The sound signal classification results include the characteristic information of motor operation sound, fan blade impact sound, and bearing abnormal sound. The correlation calculation results include the intensity correlation information of vibration and noise, frequency distribution matching data, and correlation coefficient. The current pattern analysis results include the current intensity change pattern under various speeds, the current peak mark data set, and the fan blade speed and current relationship curve. The current stability assessment information includes the frequency and intensity of current fluctuations, abnormal current event statistics, and current stability rating scores. The fan fault identification results include bearing damage diagnosis data, motor overheating signal characteristics, and fault type classification results. The fan operation monitoring records include fan efficiency evaluation data, performance degradation trend analysis results, and equipment predicted service life.

[0025] See also Figure 2 and Figure 3 , the noise data acquisition module includes: The sound signal acquisition submodule is based on the sound acquisition device, which collects the sound of the fan in real time and converts it into digital signals to generate digital sound data; In the sound signal acquisition submodule, based on the sound acquisition device, a microphone array is used to capture the sound fluctuations generated when the fan is running, and the sound waves are converted into digital signals through a digital signal converter. The conversion process includes sampling rate selection, bit depth setting and signal enhancement processing. The sampling rate is set to 44.1kHz to ensure the sound quality, and the bit depth is selected to be 16 or 24 bits to improve the dynamic range and accuracy of the sound data. The signal enhancement processing includes denoising and sound intensity standardization to optimize the clarity and availability of sound data in different operating environments to obtain digitized sound data.

[0026] The sound wave analysis submodule is run to analyze the frequency and amplitude changes of the sound wave data based on the digitized sound data to obtain the sound wave characteristic data; In the running sound wave analysis submodule, based on the digitized sound data, the fast Fourier transform algorithm is used to analyze the target data, and the time series sound data is converted into frequency domain representation. The conversion process reveals the frequency composition and amplitude information of the data. The data is windowed during the analysis, and the Hamming window or Hanning window is used to reduce the edge effect of the time domain signal. The FFT transform is performed to obtain accurate measurement of frequency and amplitude. According to the FFT results, the dominant frequency components and the corresponding amplitude sizes in the sound data are determined. The target data is refined into sound wave characteristic data, which provides the necessary basis for subsequent sound classification.

[0027] The operation sound classification submodule identifies and classifies various sounds generated by the fan operation based on the acoustic wave characteristic data, including the motor operation sound, fan blade impact sound, and bearing abnormal sound, and generates the sound signal classification result; In the operating sound classification submodule, based on the acoustic characteristic data, machine learning classification algorithms, support vector machines or deep neural networks are used to learn and distinguish different types of sound events, such as normal motor operation sound, fan blade impact sound and bearing abnormal sound. The process includes feature extraction, extracting features that are helpful for classification from the acoustic characteristic data, such as frequency peak, energy density and spectrum attenuation rate, and training the classification model according to the target features. The training process includes selecting a suitable training set and setting cross-validation to optimize model parameters to prevent overfitting and ensure the generalization ability of the model. The classification results are verified for accuracy on the test set to generate sound signal classification results. The target results provide real-time and effective data support for fan maintenance.

[0028] See also Figure 2 and Figure 4 , the vibration noise correlation analysis module includes: The fan vibration monitoring submodule uses vibration sensors to collect and record the fan vibration data in real time based on the sound signal classification results and generates vibration data records; In the fan vibration monitoring submodule, vibration sensors such as accelerometers and speedometers are configured. The target sensors are fixed on the key components of the fan to capture the vibration generated by mechanical movement in real time. The data acquisition process includes continuous sampling of signals and conversion of analog signals into digital signals. The sampling frequency is usually set to be twice higher than the fan operating frequency, complying with the Nyquist sampling theorem to ensure the integrity and validity of the signal. The collected vibration data is first time-synchronized to ensure that it corresponds to the time of the fan operating status data, and then filtered. Low-pass, high-pass or band-pass filters are used to remove useless frequency components, enhance the vibration frequency related to fan failures, and convert them into digital vibration data, which provides basic data for subsequent in-depth analysis and generates vibration data records.

[0029] The vibration signal analysis submodule analyzes the frequency distribution and intensity changes of the vibration signal based on the vibration data records, extracts the key frequency and amplitude characteristics of the vibration signal, and obtains the vibration characteristic data; In the vibration signal analysis submodule, fast Fourier transform is used as a signal processing technology to perform frequency domain analysis on the vibration data records collected from the fan. FFT processing reveals the spectral characteristics of the vibration signal and identifies high-energy frequency components. The target components are usually associated with mechanical faults such as imbalance, misalignment or bearing damage. Amplitude analysis is used to evaluate the intensity of each major frequency component. By calculating the root mean square value of the signal, the overall vibration energy is obtained to determine the health status of the equipment. The extracted key frequency and amplitude characteristics of the vibration signal will be used for further mechanical condition monitoring and fault diagnosis to obtain vibration characteristic data.

[0030] The correlation analysis submodule analyzes the correlation between the sound signal and the vibration data based on the vibration characteristic data, calculates the correlation coefficient between the vibration and the noise by comparing the intensity and frequency distribution at the same time point, and generates the correlation analysis results; The specific formula for calculating the correlation coefficient between vibration and noise is: ; in, Represents the correlation coefficient, which shows the strength of the relationship between vibration data and sound data. represents the total number of data points, indicating the total number of time points considered in the analysis, Represents a specific sequence number, used to indicate the position in the entire data set. Represents vibration data at a point in time The strength of Represents the sound signal at the same time point The strength of Represents the average intensity of vibration data, Represents the average intensity of the sound data.

[0031] formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: The formula is used to calculate the Pearson correlation coefficient between the sound signal and the vibration data. The coefficient measures the degree of linear correlation between the two variables. The result is used to evaluate the relationship between the vibration and sound of the fan to help fault detection and performance monitoring. Parameter meaning and setting value: is the total number of data points, assuming it is 5, reflecting the number of samples selected.

[0032] For time point The vibration intensities on the are assumed to be 10, 10.5, 11, 11.5, and 12 respectively; For time point The sound intensities are assumed to be 70, 71, 72, 73, and 74 respectively; is the average value of the vibration intensity, m; is the average value of the sound intensity, ; Substitute the parameters into the formula for calculation: Calculate the numerator: ; Calculate the denominator: ; Calculate the correlation coefficient: ; result It showed a positive correlation between vibration data and sound data, indicating that the vibration characteristics of the fan are related to the sound output. The results are used to monitor and diagnose the equipment status.

[0033] See also Figure 2 and Figure 5 , the operating current acquisition module includes: The operation status monitoring submodule monitors and records the current data and fan blade speed in real time based on the results of the mutual relationship analysis, and obtains the current and speed data; In the operation status monitoring submodule, multiple current and speed sensors are deployed at key locations of the wind turbine. The target sensors are used to capture real-time data of current and speed. The sensor output is converted into a digital signal through an analog-to-digital converter to ensure data accuracy and high resolution. Data synchronization processing is used to ensure time alignment of current and speed data and improve the accuracy of data analysis. During the data acquisition process, the readings of each sensor undergo initial signal processing, including filtering and denoising, to reduce the impact of environmental and operational noise and enhance signal reliability. The obtained current and speed data are used to observe the behavior patterns of the wind turbine under different operating conditions, providing basic data for further analysis.

[0034] The operation characteristic analysis submodule analyzes the current changes under various speed conditions based on the current and speed data, identifies the current characteristics under various speed conditions, and generates synchronous current analysis results; In the operation characteristics analysis submodule, based on the collected current and speed data, time-frequency analysis techniques such as wavelet transform are used to explore the changing characteristics of current under various speed conditions. Wavelet transform is used to analyze non-stationary signals, provide local frequency information about the signal, and realize the analysis of instantaneous changes in the current signal, including decomposing the current signal, separating the composition of each frequency band, analyzing the energy distribution in each frequency band, and identifying the pattern of current changes at different speeds. By comparing the current characteristics at different speeds, the analysis team can identify which changes are normal and which may indicate potential equipment problems, and generate synchronous current analysis results. The target results are crucial for optimizing wind turbine operation and maintenance plans.

[0035] The operation mode analysis submodule analyzes the change mode of the current waveform under various working conditions based on the synchronous current analysis results, identifies the normal current fluctuation mode, sets the abnormal current detection threshold, and generates the current mode analysis results; In the operation mode analysis submodule, based on the synchronous current analysis results obtained in the previous step, the behavior patterns of the current waveform under different working conditions are explored. Statistical analysis methods and machine learning techniques, such as random forests or support vector machines, are used to analyze the patterns of the current waveform, including normal and abnormal fluctuations under different working conditions. This helps determine the typical characteristics and abnormal indicators of the current waveform, and sets the abnormal current detection threshold. The target threshold is set based on historical data and pre-defined performance standards to ensure that current fluctuations that deviate from the normal mode can be automatically identified during the operation of the wind turbine, and the current status can be monitored in real time to prevent possible failures. The generated current pattern analysis results provide strong data support for the maintenance team and enhance the reliability and safety of wind turbine operation.

[0036] See also Figure 2 and Figure 6 , the abnormal current detection module includes: The abnormal data extraction submodule identifies the irregular fluctuations in the current data based on the current pattern analysis results, compares them with the abnormal current detection threshold, records the abnormal intensity and frequency, and generates abnormal current data records; In the abnormal data extraction submodule, based on the current pattern analysis results, threshold matching technology is used to identify and record irregular fluctuations in current data. By setting dynamic thresholds based on statistical analysis, it automatically adapts to different operating conditions and environmental changes. The threshold is determined based on the mean and standard deviation of historical current data and the typical current fluctuation range during mechanical operation. During the detection process, any current change that exceeds the target preset threshold is considered abnormal. The system automatically records the intensity and frequency of the target abnormality. The target record includes a timestamp, the specific value of the abnormal current, and the deviation compared to normal operation. The data record helps technicians track specific abnormal events, provides an important basis for further analysis, and generates abnormal current data records.

[0037] The abnormal mode analysis submodule analyzes the abnormal current mode and conditions based on the abnormal current data records, identifies the causes of the abnormal current, including motor overload, short circuit, power supply fluctuation, and poor contact, and obtains the abnormal current analysis results; In the abnormal pattern analysis submodule, based on the collected abnormal current data records, pattern recognition algorithms, such as cluster analysis and decision tree analysis, are used to analyze the specific patterns and triggering conditions of the current anomaly. Through the target algorithm, common abnormal patterns are identified from batches of abnormal events and associated with known motor fault types, including overload, short circuit, power supply fluctuation, and poor contact. During the analysis process, cluster analysis helps to aggregate batches of abnormal data into meaningful groups and discover characteristic patterns of different fault types. Decision trees are used to determine the specific cause of the fault based on the abnormal characteristics. For example, a sudden increase in current may indicate a short circuit, and periodic fluctuations in current may be caused by unstable power supply. The generated current anomaly analysis results provide a detailed basis for fault diagnosis and enhance the efficiency and accuracy of fault handling.

[0038] The stability real-time calculation submodule evaluates the stability of the current when the wind turbine is running in real time based on the current anomaly analysis results, and obtains the current stability evaluation information; In the real-time stability calculation submodule, based on the current anomaly analysis results, real-time data analysis technology is used to conduct real-time evaluation of wind turbine current stability. Time series analysis and real-time monitoring algorithms, such as sliding window technology and anomaly detection algorithms, are integrated to dynamically track current stability indicators. By calculating the sliding mean and coefficient of variation of current data, the stability of the current is reflected in real time. Variations beyond the predefined range trigger an alarm. The target real-time analysis results provide operators with immediate stability status, ensure that the wind turbine operates under optimal operating conditions, prevent potential risks caused by current instability, and obtain current stability evaluation information. The target information is key data for maintenance strategy adjustment and fault prevention.

[0039] See also Figure 2 and Figure 7 , the equipment fault diagnosis module includes: The abnormal event recording submodule analyzes the abnormal patterns of current and sound data based on the current stability assessment results, including the time and intensity of the abnormality, records the occurrence time of the abnormal event and the corresponding sound data, and obtains the abnormal event data set; In the abnormal event recording submodule, the current stability assessment results and sound monitoring data are comprehensively analyzed. Signal processing techniques, such as high-pass filters and spectrum analysis, are used to perform preliminary processing on the current and sound data, respectively, to screen signals with abnormal patterns, separate abnormal signals from background noise, and improve the accuracy of abnormal detection. The specific timestamp and intensity of each abnormal event are recorded, and combined with the spectral characteristics of the sound data, an abnormal event data set is formed. The data set includes time and intensity information, which provides rich information resources for subsequent fault analysis. The obtained abnormal event data set is the basis for subsequent analysis, ensuring the integrity of the data and the reliability of the analysis.

[0040] The similarity calculation submodule is based on the abnormal event data set and uses the sound and current data of known fault modes to calculate the similarity between abnormal sound signals and current data and multiple fault modes, and obtains the fault mode comparison record; In the similarity calculation submodule, the abnormal event data set is used to calculate the similarity between the abnormal sound signal and current data and the known fault mode using the cosine similarity algorithm. The formula is: ; In the formula, is the similarity, which is used to measure the relative direction relationship between two signals in the vector space. and Represents the first data points, Detailed explanation of the formula and the process of formula calculation and derivation: Assume that the abnormal sound signal feature vector is , the known fault mode sound feature vector is ,The target features can be extracted through the frequency energy distribution (unit normalization), which represents the frequency intensity characteristics of each signal, Calculation steps: ; ; result It shows that there is a high degree of similarity between abnormal sound signals and sound signals of known fault modes. The results provide a clear direction for fault diagnosis and lay the foundation for fault analysis.

[0041] The diagnosis result generation submodule identifies the fault type of the fan, including bearing damage and motor overheating, based on the fault mode comparison record, and records the time information of the fault occurrence to generate the fan fault identification result; In the diagnosis result generation submodule, the fault mode comparison records are used to identify the fault type of the fan through decision analysis. In the process, the fault mode comparison records are comprehensively analyzed to determine which patterns have the highest match with the current abnormal data. For example, if the abnormal data shows that the current suddenly increases and is accompanied by high-frequency vibration sounds, it is judged to be bearing damage. If the data shows that the current is continuously too high and the temperature is abnormal, it is diagnosed as motor overheating. Adding a time label to each diagnostic result and recording the time when the fault occurred is crucial for tracking the development of the fault and formulating a maintenance plan. The generated fan fault identification result includes the fault type, the time of occurrence of the fault and the possible cause, and provides comprehensive fault diagnosis information to help operators respond in a timely manner and take appropriate maintenance measures.

[0042] See also Figure 2 and Figure 8 , the performance degradation prediction module includes: The operating efficiency calculation submodule uses the fan fault identification results and the current data at various fan speeds to analyze and record the fan operating efficiency and generate efficiency analysis data; In the operation efficiency calculation submodule, based on the results of fan fault identification, data analysis technology is used to record and analyze the current consumption data under various speed conditions to evaluate the operation efficiency of the fan. Load analysis and energy consumption models are used to compare the current data at each speed to calculate the difference between the real-time energy consumption and the theoretical energy consumption. The difference reflects the energy efficiency status of the fan in actual operation. Regression analysis technology is used to estimate the energy efficiency level of the fan based on the relationship between current and output power. The target calculation results provide data support for subsequent maintenance and adjustment. The generated efficiency analysis data is a detailed performance report, which includes the energy efficiency score of the fan under different conditions and potential energy consumption problems. The target information is of great value for optimizing fan configuration and improving energy efficiency.

[0043] The degradation rate calculation submodule evaluates the performance degradation trend of the fan based on the efficiency analysis data through time series analysis, including analyzing the speed of performance degradation and generating performance degradation trend information; In the degradation rate calculation submodule, based on the efficiency analysis data, time series analysis technology is used to evaluate the performance degradation trend of the fan. The autoregressive sliding average model is applied to perform trend analysis on the efficiency data to predict the rate of performance degradation and possible failure time points. During the analysis process, the seasonal changes in fan operation and the impact of frequency of use on performance are considered to accurately simulate and predict the long-term performance trend. By calculating the rate of performance degradation in each monitoring cycle, comprehensive performance degradation trend information is generated. The target information includes degradation rate and predicted failure occurrence period, providing a basis for formulating preventive maintenance plans.

[0044] The operating life prediction submodule predicts the expected life of the fan based on the performance degradation trend information, and combines the failure frequency of the fan to predict the maintenance cycle and adjust the maintenance schedule, and generate the fan operation monitoring record; In the operating life prediction submodule, the performance degradation trend information is used to use the prediction model to calculate the expected life of the fan and its maintenance cycle. Survival analysis and reliability theory are used to predict the fan life and failure interval based on performance degradation data and historical fault records. Through target analysis, the remaining effective operating time of the fan is predicted, and the optimal maintenance time point is specified to maximize the operating efficiency of the fan and reduce downtime. The target prediction data is integrated to form a fan operation monitoring record. The target record lists the expected maintenance schedule and recommended operating strategies to ensure that the fan maintains optimal performance throughout its life cycle.

[0045] See also Fig. 9A noise and current detection method is provided, and the noise and current detection method is performed based on the above-mentioned wind turbine operation status comprehensive monitoring system, and includes the following steps: S1: Based on the sound collection equipment, the sound signals of the fan in operation are collected in real time, and the frequency and amplitude of the signals are analyzed to extract key sound features, identify and classify the various sounds generated by the fan operation, and generate sound signal classification results; S2: Based on the sound signal classification results, collect vibration data, analyze the time synchronization and frequency similarity of the sound and vibration data, calculate the correlation coefficient, and generate the mutual relationship calculation results; S3: Based on the calculation results of the mutual relationship, the current data is monitored in real time and the fan blade speed is recorded. The changes in the current waveform under various speeds are analyzed, the regular characteristics of the current changes are identified, and the current pattern analysis results are generated; S4: Based on the current pattern analysis results, analyze the current data, identify and record abnormal fluctuations in the current, including peak intensity and abnormal frequency, evaluate the stability of the operating current, and establish current stability evaluation information; S5: Based on the current stability assessment information, the fault type is identified by comparing the current and sound signal patterns with known fault modes. The current data of the fan at various speeds is used to calculate the fan operating efficiency and evaluate the performance degradation trend, and generate a fan operation monitoring record.

[0046] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Comprehensive monitoring system for fan operation status, characterized by: The system comprises: The noise data acquisition module is based on the sound acquisition equipment, collects the sound of the fan operation, analyzes the frequency and amplitude of the sound wave, identifies and classifies the various sounds generated by the fan operation, and obtains the sound signal classification results; The vibration noise correlation analysis module uses a vibration sensor to collect and record the vibration data of the fan in real time based on the sound signal classification result, analyzes the correlation between the vibration signal and the sound signal, and generates a correlation calculation result; The operating current acquisition module collects the current data and the fan blade speed in real time when the fan is running based on the calculation result of the mutual relationship, analyzes the change mode of the current under various speed conditions, and generates a current mode analysis result; The abnormal current detection module analyzes the current data based on the current mode analysis result, detects abnormal fluctuations in the current data, evaluates the stability of the current when the fan is running, and establishes current stability evaluation information; The equipment fault diagnosis module identifies the type of fault based on the current stability evaluation information by comparing the current and sound signal patterns with a plurality of known fault modes, and generates a fan fault identification result; The performance degradation prediction module uses the fan fault identification result to calculate the fan operation efficiency according to the fan current data at various speeds, evaluates the fan performance degradation trend, predicts the fan service life, and obtains the fan operation monitoring record.

2. The comprehensive monitoring system for fan operation status according to claim 1 is characterized in that: The sound signal classification result includes the motor running sound characteristic information, the fan blade impact sound characteristic information, and the bearing abnormal sound characteristic information. The correlation calculation result includes the intensity correlation information of vibration and noise, frequency distribution matching data, and correlation coefficient. The current pattern analysis result includes the current intensity change pattern under multiple speeds, the current peak mark data set, and the fan blade speed and current relationship curve. The current stability evaluation information includes the frequency and intensity of current fluctuations, abnormal current event statistics, and current stability rating scores. The fan fault identification result includes bearing damage diagnosis data, motor overheating signal characteristics, and fault type classification results. The fan operation monitoring record includes fan efficiency evaluation data, performance degradation trend analysis results, and equipment predicted service life.

3. The comprehensive monitoring system for wind turbine operation status according to claim 1 is characterized in that: The noise data acquisition module comprises: The sound signal acquisition submodule is based on the sound acquisition device, which collects the sound of the fan in real time and converts it into digital signals to generate digital sound data; The sound wave analysis submodule is run to analyze the frequency and amplitude changes of the sound wave data based on the digitized sound data to obtain sound wave characteristic data; The operation sound classification submodule identifies and classifies various sounds generated by the operation of the fan based on the acoustic wave characteristic data, including motor operation sound, fan blade impact sound, and bearing abnormal sound, and generates a sound signal classification result.

4. The comprehensive monitoring system for wind turbine operation status according to claim 1 is characterized in that: The vibration noise correlation analysis module includes: The fan vibration monitoring submodule collects and records the vibration data of the fan in real time using a vibration sensor based on the sound signal classification result, and generates a vibration data record; The vibration signal analysis submodule analyzes the frequency distribution and intensity change of the vibration signal based on the vibration data record, extracts the key frequency and amplitude characteristics of the vibration signal, and obtains vibration characteristic data; The correlation analysis submodule analyzes the correlation between the sound signal and the vibration data based on the vibration characteristic data, calculates the correlation coefficient between the vibration and the noise by comparing the intensity and frequency distribution at the same time point, and generates a correlation analysis result.

5. The comprehensive monitoring system for wind turbine operation status according to claim 4 is characterized in that: The specific formula for calculating the correlation coefficient between vibration and noise is: ； in, Represents the correlation coefficient, which shows the strength of the relationship between vibration data and sound data. represents the total number of data points, indicating the total number of time points considered in the analysis, Represents a specific sequence number, used to indicate the position in the entire data set. Represents vibration data at a point in time The strength of Represents the sound signal at the same time point The strength of Represents the average intensity of vibration data, Represents the average intensity of the sound data.

6. The comprehensive monitoring system for wind turbine operation status according to claim 1 is characterized in that: The operating current acquisition module comprises: The operation status monitoring submodule monitors and records the current data and the fan blade speed in real time when the fan is running based on the mutual relationship analysis result to obtain the current and speed data; The operation characteristic analysis submodule analyzes the current changes under various speed conditions based on the current and speed data, identifies the current characteristics under various speed conditions, and generates synchronous current analysis results; The operation mode analysis submodule analyzes the change mode of the current waveform under various working conditions based on the synchronous current analysis result, identifies the normal current fluctuation mode, sets the abnormal current detection threshold, and generates the current mode analysis result.

7. The comprehensive monitoring system for wind turbine operation status according to claim 1 is characterized in that: The abnormal current detection module comprises: The abnormal data extraction submodule identifies the unconventional fluctuations in the current data based on the current pattern analysis result by comparing it with the abnormal current detection threshold, records the abnormal intensity and frequency, and generates abnormal current data records; The abnormal mode analysis submodule analyzes the mode and conditions of the abnormal current based on the abnormal current data record, identifies the cause of the abnormal current, including motor overload, short circuit, power supply fluctuation, poor contact, and obtains the abnormal current analysis result; The stability real-time calculation submodule evaluates the stability of the current when the wind turbine is running in real time based on the current anomaly analysis result to obtain current stability evaluation information.

8. The integrated monitoring system for wind turbine operation status according to claim 1 is characterized in that: The equipment fault diagnosis module comprises: The abnormal event recording submodule analyzes the abnormal patterns of the current and sound data based on the current stability evaluation result, including the time and intensity of the abnormality, records the occurrence time of the abnormal event and the corresponding sound data, and obtains an abnormal event data set; The similarity calculation submodule calculates the similarity between the abnormal sound signal and the current data and a plurality of fault modes based on the abnormal event data set and using the sound and current data of the known fault modes to obtain a fault mode comparison record; The diagnosis result generation submodule identifies the fault type of the fan based on the fault mode comparison record, including bearing damage and motor overheating, and records the time information of the fault occurrence to generate a fan fault identification result.

9. The comprehensive monitoring system for wind turbine operation status according to claim 1, characterized in that: The performance degradation prediction module comprises: The operation efficiency calculation submodule uses the fan fault identification result and the current data under various fan speeds to analyze and record the operation efficiency of the fan and generate efficiency analysis data; The decay rate calculation submodule evaluates the performance degradation trend of the fan through time series analysis based on the efficiency analysis data, including analyzing the speed of performance decay and generating performance degradation trend information; The operating life prediction submodule predicts the expected life of the fan based on the performance degradation trend information, predicts the maintenance cycle and adjusts the maintenance schedule in combination with the failure frequency of the fan, and generates a fan operation monitoring record.

10. A noise and current detection method, characterized in that: The wind turbine operating status comprehensive monitoring system according to any one of claims 1 to 9 comprises the following steps: Based on the sound collection equipment, the sound signals of the fan in operation are collected in real time, and the frequency and amplitude of the signals are analyzed to extract key sound features, identify and classify the various sounds generated by the fan operation, and generate sound signal classification results; Based on the sound signal classification result, vibration data is collected, time synchronization and frequency similarity of the sound and vibration data are analyzed, and correlation coefficients are calculated to generate a correlation calculation result; Based on the calculation results of the mutual relationship, the current data is monitored in real time and the fan blade speed is recorded, the changes in the current waveform under various speeds are analyzed, the regular characteristics of the current changes are identified, and the current pattern analysis results are generated; Based on the current pattern analysis results, analyze the current data, identify and record abnormal fluctuations in the current, including peak intensity and abnormal frequency of occurrence, evaluate the stability of the operating current, and establish current stability evaluation information; Based on the current stability assessment information, the fault type is identified by comparing with the current and sound signal patterns of known fault modes, and the current data of the fan at various speeds is used to calculate the fan operating efficiency and evaluate the performance degradation trend, thereby generating a fan operation monitoring record.

Images