A tunnel fan operation detection method, fan analyzer, medium and product

Abstract

A method for detecting the operation of a tunnel fan, a fan analyzer, a medium and a product, which relate to the field of equipment detection, and the method comprises: generating a detection request according to the equipment identification information of the fan analyzer and the target detection fan, and sending the detection request to the ventilation control system; receiving the real-time vibration data, real-time displacement data and historical maintenance data of the target detection fan returned by the ventilation control system; determining the vibration spectrum characteristics of the target detection fan based on the real-time vibration data; determining the axis trajectory characteristics of the target detection fan based on the real-time displacement data; inputting the vibration spectrum characteristics, the axis trajectory characteristics and the historical maintenance data into an operation evaluation model to obtain the operation status score of the target detection fan; generating a maintenance recommendation report for the target detection fan based on the operation status score. Implementation of this application can monitor the operation of tunnel fans and reduce the dispatching cost of maintenance personnel.

Description

Technical Field

[0001] The present application relates to the field of equipment detection, and in particular to an operation detection method, a fan analyzer, a medium and a product of a tunnel fan. Background Art

[0002] With the acceleration of urbanization, tunnel engineering plays an increasingly important role in urban transportation. The tunnel ventilation system is a key equipment to ensure the safe operation of the tunnel. The operating status of its core component, the fan, directly affects the air quality and personnel safety in the tunnel. Therefore, real-time monitoring and timely maintenance of tunnel fans are of great significance.

[0003] In related technologies, tunnel fan detection is mainly implemented using an online vibration monitoring system. The system installs vibration sensors at key locations such as the fan main bearing seat, and transmits the collected vibration signals to the control center, which determines the equipment operating status based on the vibration amplitude. When the vibration value exceeds the preset threshold, the system will issue an alarm signal to prompt the operation and maintenance personnel to conduct inspections and maintenance.

[0004] However, because the relevant technology will alarm after the vibration exceeds the limit, the fan equipment may be in a serious fault state at this time and need to be inspected or replaced on site. Different equipment often has fault alarms at different time points, which will increase the scheduling cost of maintenance personnel. Summary of the invention

[0005] The present application provides a tunnel fan operation detection method, a fan analyzer, a medium and a product, which are used to perform operation detection on the tunnel fan and reduce the dispatch cost of maintenance personnel.

[0006] In a first aspect, the present application provides an operation detection method for a tunnel fan, which is applied to a fan analyzer, and the method includes: determining a target detection fan based on user settings, generating a detection request according to the equipment identification information of the fan analyzer and the target detection fan, and sending the detection request to the ventilation control system; receiving real-time vibration data, real-time displacement data and historical maintenance data of the target detection fan returned by the ventilation control system after successfully authenticating the equipment identification information; calculating a vibration frequency domain signal based on the real-time vibration data, and performing a spectrum analysis on the vibration frequency domain signal to determine the vibration spectrum characteristics of the target detection fan; constructing an axis motion trajectory diagram based on the real-time displacement data, and performing a trajectory feature analysis on the axis motion trajectory diagram to determine the axis trajectory characteristics of the target detection fan; inputting the vibration spectrum characteristics, axis trajectory characteristics and historical maintenance data into an operation evaluation model to obtain an operation status score of the target detection fan; and generating a maintenance recommendation report for the target detection fan based on the operation status score.

[0007] In the above embodiment, the fan analyzer determines the target detection fan based on the user settings, obtains real-time vibration and displacement data, and performs spectrum and trajectory analysis. It then evaluates the operating status in combination with historical maintenance data, and finally generates a maintenance recommendation report, thereby achieving comprehensive monitoring and early warning of the fan operating status, being able to detect potential faults in a timely manner and arrange maintenance, reducing maintenance costs and the risk of equipment damage.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the steps of determining the target detection fan based on user settings, generating a detection request according to the device identification information of the fan analyzer and the target detection fan, and sending the detection request to the ventilation control system, the method also includes: receiving an error identification code returned by the ventilation control system after authentication fails; when the error identification code indicates that the target detection fan does not exist, sending a fan data synchronization request containing the current data version to the cloud data center; receiving the fan incremental information returned by the cloud data center after verifying the current data version, and updating the fan display list according to the fan incremental information.

[0009] In the above embodiment, the fan analyzer sets a fan data synchronization mechanism, and can update the fan data from the cloud when the detection request authentication fails, thereby ensuring the real-time and accuracy of the fan display list and improving the reliability of device identification and detection.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of receiving the error identification code returned by the ventilation control system after authentication fails, the method also includes: when the error identification code is device authentication failure, obtaining the hardware serial number and security authentication key of the fan analyzer; encrypting the hardware serial number and security authentication key based on a preset encryption algorithm to obtain a device authentication code, and sending the device authentication code to the authentication server; receiving the device authorization authentication and device authorization time limit returned by the authentication server, and regenerating the device identification information and detection request based on the device authorization authentication.

[0011] In the above embodiment, the wind turbine analyzer introduces a device authentication mechanism, and generates a device authentication code through the hardware serial number and the security authentication key, thereby realizing secure access and authorization management of the wind turbine analyzer and ensuring the security and controllability of the detection system.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of generating a maintenance recommendation report for the target detection fan based on the operating status score specifically includes: grading the operating status score to determine the score interval corresponding to the operating status score; the scoring interval includes a normal operating interval, a warning interval and a fault interval; when the operating status score is in the warning interval, determining the abnormal mode corresponding to the vibration spectrum characteristics and the axis trajectory characteristics, and matching historical fault cases according to the abnormal mode; based on the historical fault cases, generating a maintenance recommendation report including fault warning information, maintenance suggestions and maintenance cycle suggestions; when the operating status score is in the fault interval, generating an emergency maintenance report including fault diagnosis results, maintenance plans and spare parts requirements.

[0013] In the above embodiment, the fan analyzer performs graded processing on the operating status scores and adopts different processing strategies for the warning and fault intervals, thereby achieving precise fault warning and improving maintenance efficiency.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating a maintenance recommendation report for the target detection wind turbine based on the operating status score, the method also includes: obtaining the repair status score of the target detection wind turbine after maintenance; when the repair status score is higher than a preset acceptance threshold, generating a maintenance acceptance report including fault elimination verification based on the operating status score and the repair status score.

[0015] In the above embodiment, the fan analyzer evaluates and verifies the maintenance effect by introducing a maintenance acceptance mechanism, thereby ensuring the maintenance quality and avoiding the recurrence of problems caused by incomplete maintenance.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining the repair status score of the target detection fan after maintenance, the method also includes: when the repair status score is not higher than a preset acceptance threshold, collecting test vibration data and test axis trajectory of the target detection fan at different speed gears; based on the test vibration data and the test axis trajectory, determining the remaining fault types of the target detection fan; and generating secondary maintenance recommendations based on the remaining fault types.

[0017] In the above embodiment, the fan analyzer performs multi-speed testing and analysis when the maintenance acceptance fails, identifies the remaining faults and gives secondary maintenance suggestions, thereby ensuring the integrity and effectiveness of the maintenance.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating a maintenance recommendation report for a target detection fan based on an operating status score, the method further includes: obtaining a maintenance report set and fan location information for multiple target detection fans; extracting the fault severity, equipment importance and maintenance difficulty of multiple target detection fans in the maintenance report set, and determining the maintenance urgency index of multiple target detection fans; generating an inspection path based on the maintenance urgency index of multiple target detection fans, fan location information and inspection personnel information.

[0019] In the above embodiment, the fan analyzer generates an optimal inspection path based on factors such as fault severity, equipment importance, and maintenance difficulty, thereby improving inspection efficiency and achieving optimal allocation of maintenance resources.

[0020] In a second aspect, an embodiment of the present application provides a wind turbine analyzer, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the wind turbine analyzer to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a wind turbine analyzer, enables the wind turbine analyzer to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a wind turbine analyzer, the wind turbine analyzer executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It can be understood that the wind turbine analyzer provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of a fan operation detection method based on real-time data collection and multi-dimensional analysis, combined with a comprehensive evaluation mechanism of vibration frequency domain analysis, axis trajectory characteristics and historical maintenance data, and the use of an operation evaluation model for status scoring, the fan operation status can be accurately grasped, effectively solving the problem of the existing technology that only relies on a single vibration threshold to judge and is difficult to detect potential faults in a timely manner, thereby achieving early warning and accurate diagnosis of fan faults, reducing maintenance costs and equipment damage risks.

[0025] 2. Due to the adoption of a device authentication mechanism based on hardware serial number and security authentication key, a device authentication code is generated through a preset encryption algorithm and server verification is performed to obtain device authorization authentication and authorization time limit. Therefore, a strict device access and authentication process is established, which effectively solves the system security risks caused by the lack of device authentication mechanism in the existing technology, thereby realizing the safe and controllable operation of the detection system and ensuring the security of data transmission and control.

[0026] 3. Due to the adoption of a hierarchical processing mechanism based on operating status scoring, different processing strategies are adopted for the warning interval and the fault interval respectively. By matching historical fault cases through abnormal patterns and generating corresponding maintenance suggestions, targeted measures can be taken according to the severity of the fault, effectively solving the problems of single fault handling scheme and weak maintenance guidance in the existing technology, thereby realizing the precision and efficiency of fault handling, and improving the timeliness and effectiveness of equipment maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for detecting the operation of a tunnel fan in an embodiment of the present application; Figure 2 is another flow chart of the tunnel fan operation detection method in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of a fan analyzer in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0031] In a large tunnel construction project, the operator is responsible for managing more than 200 tunnel fans. These fans are distributed in more than 40 tunnels, with the length of a single tunnel ranging from 2 kilometers to 8 kilometers. To ensure the air quality and construction safety of the tunnels, it is necessary to ensure the continuous and stable operation of the fans. However, due to the large number of fans and their wide distribution, it is difficult for operation and maintenance personnel to detect and handle all fan failures in a timely manner.

[0032] In the related art, the fan failure detection can be achieved by using a vibration monitoring system based on a fixed threshold. The system collects data through a single vibration sensor. When the vibration value exceeds the preset threshold, an alarm is triggered and maintenance personnel need to go to the site for inspection and maintenance. The following introduces the scenario of using the tunnel fan operation detection method in the related art.

[0033] A tunnel operating unit uses a traditional online vibration monitoring system for wind turbine management. The system installs vibration sensors on each wind turbine and sets fixed alarm thresholds. When the vibration value of a wind turbine exceeds the threshold, the system sends an alarm message to the maintenance personnel. For example, in February 2024, a bearing failure occurred in the No. 3 wind turbine in Section A, and the vibration value exceeded the limit alarm. When the maintenance personnel arrived at the scene, they found that the bearing was seriously damaged and needed to be replaced. A week later, a similar failure occurred in the No. 7 wind turbine in the adjacent Section B. This passive maintenance method causes maintenance personnel to frequently travel between different sections, which not only increases labor costs, but also makes it difficult to preventively detect potential faults.

[0034] By using the tunnel fan operation detection method in the embodiment of the present application, through multi-dimensional data collection and analysis, equipment status scoring mechanism and intelligent inspection planning, early warning of fan failure and optimal allocation of maintenance resources are achieved, which not only improves the accuracy of fault diagnosis, but also reduces the scheduling cost of maintenance personnel. The following introduces the scenario of using the tunnel fan operation detection method in the present application.

[0035] The operating unit introduced an intelligent detection system based on a fan analyzer. The system can not only collect vibration data in real time on site, but also conduct comprehensive analysis in combination with displacement sensor data. Through real-time analysis of the vibration spectrum and axis trajectory, the system can detect equipment abnormalities at an early stage. For example, during a routine inspection, the system found that multiple fans in section C had similar abnormal characteristics. By analyzing historical data, it was determined that these fans may have bearing problems in the next two months. Based on this, the maintenance personnel formulated a unified preventive maintenance plan and completed the maintenance work of all fans in one inspection, avoiding multiple round trips.

[0036] It can be seen that the operation detection method of the tunnel fan in the embodiment of the present application can not only realize real-time monitoring of the equipment status, but also effectively solve the problems of difficulty in predicting the development trend of faults and low efficiency of maintenance scheduling in traditional methods, thereby realizing the transformation of equipment maintenance from passive response to active prevention.

[0037] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the operation detection method of the tunnel fan in the embodiment of the present application.

[0038] S101. Determine a target detection fan based on user settings, generate a detection request according to device identification information of a fan analyzer and the target detection fan, and send the detection request to a ventilation control system.

[0039] Among them, the target detection fan refers to the fan equipment in the tunnel ventilation system that needs to be tested for operating status; the equipment identification information refers to the information used to uniquely identify the fan analyzer, including the equipment serial number, version number and authorization code, etc.; the detection request is the data collection application initiated by the fan analyzer to the ventilation control system, which contains information such as the request timestamp, the target detection fan number and the data type; the ventilation control system is the central control system responsible for managing and controlling the tunnel ventilation equipment.

[0040] The fan analyzer executes this step after receiving the instruction from the user to select the fan to be detected through the operation interface. Specifically, the fan analyzer first obtains the basic information of the target detection fan selected by the user from the locally stored fan device list, including the fan number, installation location and operating parameters. Then, the fan analyzer reads its own device serial number, version number and other identification information from the device configuration file, combines this information with the basic information of the target detection fan, generates a detection request message according to the predefined data format, and then sends the detection request to the ventilation control system through the preset communication interface.

[0041] In some embodiments, the process of the fan analyzer sending a detection request can be implemented in a variety of ways: Optionally, the fan analyzer can be implemented through the following steps: first, determine the priority and sampling frequency of data collection according to the operating status of the target detection fan, then write these parameters into the control field of the request message, and then use a preset encryption algorithm to encrypt the request message, and finally send it to the ventilation control system through the TCP / IP protocol; Optionally, the fan analyzer can also use a timed polling method to automatically generate a detection request at a preset time interval, and include information on multiple target detection fans in the request, and establish a long connection with the ventilation control system through the WebSocket protocol for data interaction. It is understandable that other communication protocols and data interaction methods can also be used to implement the process of sending detection requests, which is not limited here.

[0042] S102, receiving the real-time vibration data, real-time displacement data and historical maintenance data of the target detection fan returned by the ventilation control system after successful authentication of the equipment identification information.

[0043] Among them, real-time vibration data represents the vibration signals of key parts such as bearings and casings collected by sensors during the operation of the fan; real-time displacement data refers to sensor measurement data that reflects the changes in the axial position of the fan rotor; historical maintenance data is used to represent the record information of the fan's previous maintenance, including fault type, maintenance plan and replacement parts; successful authentication of equipment identification information means that the ventilation control system has verified that the identity of the fan analyzer is legal and valid.

[0044] After sending the detection request, the fan analyzer waits for the response of the ventilation control system. Specifically, when the ventilation control system completes the authentication of the fan analyzer device identification information, the fan analyzer first receives the response information containing the authentication result. If the authentication is successful, the fan analyzer then receives three types of data of the target detection fan through the preset data receiving buffer: real-time vibration waveform data collected from the vibration sensor, real-time displacement coordinate data collected from the displacement sensor, and historical maintenance records extracted from the maintenance management system. These data are packaged in a predefined data format, including information such as timestamp, data type identifier, and value.

[0045] In some embodiments, the process of the fan analyzer receiving data can be implemented in a variety of ways: Optionally, the fan analyzer can adopt an asynchronous communication mode, first establish three independent data receiving threads, which are responsible for receiving vibration data, displacement data and historical data respectively, and then cache and synchronize the received data through the data queue, and finally assemble and store the complete data packet in the local database; Optionally, the fan analyzer can also adopt a subscription-publishing mode, register a data subscription request with the ventilation control system, receive a real-time pushed data stream through the message middleware, and use a time window mechanism to process and store the data in real time. It is understandable that other data receiving and processing mechanisms can also be used to achieve reliable data acquisition, which is not limited here.

[0046] S103: Calculate the vibration frequency domain signal based on the real-time vibration data, and perform spectrum analysis on the vibration frequency domain signal to determine the vibration spectrum characteristics of the target detection fan.

[0047] Among them, the vibration frequency domain signal represents the frequency distribution characteristics obtained after Fourier transform of the time domain vibration data; spectrum analysis refers to the process of feature extraction and pattern recognition of the vibration frequency domain signal; the vibration spectrum characteristics are used to represent the set of characteristic parameters reflecting the vibration state of the fan, including the amplitude, phase angle and frequency band energy of each harmonic.

[0048] The fan analyzer performs spectrum analysis after acquiring real-time vibration data. Specifically, the fan analyzer first preprocesses the original vibration data, including data filtering, denoising, and segmentation. Then, the preprocessed time domain vibration signal is converted into a frequency domain signal using the fast Fourier transform algorithm to obtain a spectrum diagram reflecting the amplitude and phase of each frequency component. Then, feature extraction is performed on the spectrum diagram to calculate characteristic parameters such as energy distribution, harmonic ratio, and spectrum envelope of each frequency band. Finally, based on these characteristic parameters and combined with the preset feature template, the vibration spectrum characteristics of the target detection fan are determined.

[0049] Among them, the preset feature template here is constructed based on probability statistics theory. The system first performs statistical analysis on a large number of sample data in normal operation status, calculates the mean and standard deviation of each feature parameter, and establishes the confidence interval of the feature distribution. For spectral features, an adaptive weighted method is used to calculate the benchmark values ​​of different frequency bands. The weight coefficients of the low frequency band (0-100Hz), medium frequency band (100-1000Hz) and high frequency band (>1000Hz) are determined according to their importance in fault diagnosis. The dynamic update of the template adopts a sliding time window mechanism. The system continuously collects the operation data of the recent period (such as 30 days) and updates the feature benchmark value through the exponential weighted average algorithm, so that the template can adapt to the slow degradation process of equipment performance. For example, for a certain feature parameter, the new benchmark value is equal to the weighted average of the original benchmark value and the new data, and the weight coefficient decays exponentially over time, ensuring that the template can maintain stability and reflect the dynamic changes of the equipment status.

[0050] The vibration spectrum characteristics can be used to establish the vibration characteristic fingerprint of the equipment. The degree of deviation in different frequency bands is calculated by performing correlation analysis between the real-time collected spectrum and the standard spectrum. The system uses a multi-scale analysis method based on wavelet transform to decompose the vibration signal into different frequency bands and calculate the energy distribution and phase relationship of each frequency band. The amplitude ratio of the fundamental frequency and its harmonic components is obtained through Fourier series expansion, and a frequency modulation function is established in combination with the equipment speed to achieve accurate extraction of the characteristic frequencies of faults of key components such as bearings and gears. For example, when a small crack appears in a bearing, the sideband modulation phenomenon of its characteristic frequency will form a unique cluster distribution in the high-frequency region of the spectrum. By calculating the power spectrum density and inverse spectrum of this frequency band, the location and degree of development of the fault can be accurately identified.

[0051] S104, constructing an axis motion trajectory diagram based on the real-time displacement data, and performing trajectory feature analysis on the axis motion trajectory diagram to determine the axis trajectory features of the target detection fan.

[0052] Among them, the axis motion trajectory diagram represents a two-dimensional graph reflecting the motion trajectory of the fan rotor axis on a certain cross section; trajectory feature analysis refers to the process of quantitatively analyzing the shape, size, direction and other characteristics of the axis motion trajectory; the axis trajectory feature is used to represent the set of characteristic parameters that describe the laws of axis motion, including trajectory ellipticity, inclination angle and advance coefficient.

[0053] The fan analyzer performs trajectory feature analysis after acquiring real-time displacement data. Specifically, the fan analyzer first performs coordinate transformation and data synchronization on the displacement data in the X and Y directions to construct an axis motion trajectory diagram on a two-dimensional plane. Then, the trajectory diagram is subjected to geometric feature analysis to calculate parameters such as the maximum radius, minimum radius, and shape factor of the trajectory. Then, the main axis direction and degree of eccentricity of the trajectory are determined by curve fitting to obtain a quantitative feature description of the trajectory. Finally, based on these feature parameters and combined with the standard trajectory template, the axis trajectory characteristics of the target detection fan are determined.

[0054] The axis trajectory characteristics can be used to evaluate the dynamic balance state of the rotor system and the working conditions of the bearings. The rotor dynamics model is established by quantitatively analyzing the ellipticity, eccentricity and precession direction of the axis trajectory. The system uses the least squares fitting algorithm to calculate the main axis direction and shape parameters of the trajectory, extracts the geometric characteristics of the trajectory through the Fourier descriptor, and establishes the phase relationship in combination with the rotor speed vector to achieve an accurate description of the dynamic characteristics of the rotor system. When the rotor system is misaligned or dynamically unbalanced, the axis trajectory will show specific deformation characteristics. By calculating the relative damping coefficient of the trajectory in the Jeffcott rotor model, the type and severity of the fault can be quantitatively evaluated. For example, for oil film vortex faults, the system can accurately determine the development stage of the oil film vortex by analyzing the ellipticity changes and rotation direction of the axis trajectory, combined with the phase relationship of the speed multiple frequency components.

[0055] S105, input the vibration spectrum characteristics, the axis trajectory characteristics and the historical maintenance data into the operation evaluation model to obtain the operation status score of the target detection fan.

[0056] The fan analyzer performs status assessment after acquiring various feature data. Specifically, the fan analyzer first normalizes the vibration spectrum features and axis trajectory features to make features of different dimensions comparable. Then, key information such as equipment age and maintenance frequency are extracted from historical maintenance data as supplementary features. These features are then input into a pre-trained operation evaluation model, which calculates a comprehensive score based on the weight coefficients of each feature. Finally, the score result is mapped to a predefined score range to obtain the operating status score of the target detection fan.

[0057] Among them, the operation evaluation model constructs an end-to-end deep learning framework, and its feature extraction network expression is: F(x)=ReLU(BN(Conv(x))); In this expression, the input data x is a multidimensional time series consisting of the time domain waveform collected by the vibration sensor and the axis trajectory data collected by the displacement sensor. The sampling frequency is 20kHz, and each data frame contains 8192 sampling points. The convolution operation Conv uses 64 3×3 convolution kernels for feature extraction. The BatchNorm layer performs data normalization by calculating the mean and variance of the batch data. The ReLU activation function truncates negative values ​​to increase the nonlinear expression ability of the network.

[0058] The state evaluation network adopts LSTM structure, and its expression is: S(f)=σ(Wh·ht+bh); The weight matrix Wh has a dimension of 256×256 and is used to transform the hidden layer state ht. The bias vector bh has a dimension of 256×1, and the sigmoid activation function σ maps the output to the range of 0 to 1.

[0059] The final score calculation formula is: Score = α·Sv+β·St+γ·Sh; In this scoring system, the vibration feature score Sv is obtained based on spectrum analysis, with a value range of 0-100; the trajectory feature score St is obtained based on trajectory morphology analysis, with a value range of 0-100; the historical data score Sh is obtained based on the analysis of historical equipment fault records, with a value range of 0-100. The weight coefficients α, β, and γ are optimized through the back propagation algorithm, and the initial values ​​are set to 0.4, 0.4, and 0.2 respectively.

[0060] The entire model is optimized by minimizing the loss function: Loss=||Score-ScoreGT||2+λ·R(θ); the expert annotation score ScoreGT is based on the experience and judgment of the maintenance expert, the regularization term R(θ) adopts the L2 norm, and the coefficient λ is set to 0.01.

[0061] For example, the vibration spectrum analysis score Sv of a fan is 85 points, indicating that the vibration state is good; the trajectory feature analysis score St is 75 points, indicating that there is a slight axis deviation; the historical data analysis score Sh is 90 points, indicating that the historical maintenance condition is good. Substitute into the scoring formula: Score=0.4×85+0.4×75+0.2×90=82, indicating that the overall operating status of the equipment is within the normal range, but the axis deviation problem needs attention.

[0062] S106. Generate a maintenance recommendation report for the target detection fan based on the operation status score.

[0063] Among them, the maintenance recommendation report refers to a technical document containing fault diagnosis and maintenance recommendations.

[0064] The fan analyzer generates a maintenance recommendation report after obtaining the operating status score. Specifically, the fan analyzer first determines the operating level of the equipment based on the operating status score, including normal, warning and fault levels. Then, based on the current level, the corresponding diagnostic rule library is called to identify the possible fault type in combination with the vibration characteristics and trajectory characteristics. Then, the corresponding treatment plan and maintenance suggestions are matched from the maintenance knowledge base, including maintenance cycle, spare parts requirements and operating precautions. Finally, this information is organized in a standard format to generate a maintenance recommendation report.

[0065] Among them, the maintenance knowledge base adopts a hierarchical knowledge representation structure, and describes the concept system and relationship network in the field of equipment maintenance through an ontology model. At the fault diagnosis level, the system uses a reasoning mechanism based on fuzzy set theory to map multidimensional information such as vibration characteristics and trajectory characteristics to the fault space, and calculates the probability distribution of various possible faults through membership functions. The maintenance decision layer adopts a case-based reasoning method. The system calculates the similarity between the current fault characteristics and historical cases. The similarity calculation is based on the Euclidean distance of the feature vector and the expert experience weighting, and combines factors such as the equipment operating environment and maintenance costs to generate the optimal maintenance plan. During the knowledge update process, the system continuously optimizes the mapping relationship between fault characteristics and maintenance plans through an incremental learning algorithm. After the newly added maintenance cases are verified, the relevant rules of the knowledge base will be automatically updated. For example, when the system finds that the treatment plan for a certain type of fault is not effective, it will automatically adjust the feature weight and treatment strategy of this type of fault to improve the diagnostic accuracy and maintenance efficiency.

[0066] In the above embodiment, the fan analyzer achieves a comprehensive evaluation of the fan operating status by coordinating the vibration spectrum characteristics and the axis trajectory characteristics and combining the historical maintenance data. In actual applications, the fan analyzer can also directly generate the optimal inspection path based on multiple fan maintenance tasks. The following is a supplement to the scenario of this embodiment.

[0067] The operating unit further optimized the application of the detection system. The system integrates the operating data of the fans in each section through the cloud data center and establishes an equipment health scoring mechanism. When it is found that the scores of multiple fans in a certain area show a downward trend, the system will automatically generate the optimal inspection route. For example, during a routine inspection, the system found that the scores of 5 fans in Section D were close to the warning value, and immediately generated an optimal inspection route, arranging engineers with corresponding maintenance qualifications to inspect and repair them in order according to the urgency of the fault.

[0068] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the operation detection method of the tunnel fan in the embodiment of the present application.

[0069] S201. Determine a target detection fan based on user settings, generate a detection request according to device identification information of a fan analyzer and the target detection fan, and send the detection request to a ventilation control system.

[0070] Referring to step S101 , the fan analyzer sends a detection request to the ventilation control system.

[0071] S202: Receive an error identification code returned by the ventilation control system after authentication fails.

[0072] The error identification code indicates the equipment authentication result code returned by the ventilation control system.

[0073] The fan analyzer waits for the authentication result after sending the test request. Specifically, when the ventilation control system receives the test request, it will verify the legitimacy of the device identification information of the fan analyzer. If the verification fails, the system will generate a corresponding error identification code. After receiving the error identification code, the fan analyzer will parse the error type to provide a basis for the subsequent error handling process.

[0074] S203: When the error identification code indicates that the target detection wind turbine does not exist, a wind turbine data synchronization request including the current data version is sent to the cloud data center.

[0075] Among them, the fan data synchronization request represents a data packet requesting the cloud data center to update the local fan information; the current data version refers to the fan data version number stored locally by the fan analyzer; the cloud data center is used to represent a remote server that centrally stores and manages fan equipment information.

[0076] In actual applications, fans may be added, removed, or replaced in the ventilation control system, and the fan data needs to be updated accordingly. The fan analyzer executes this step when it confirms that the error type is that the target fan does not exist. Specifically, the fan analyzer first reads the current data version number from the local configuration file and encapsulates it into a data synchronization request. Then, the request is sent to the cloud data center through a preset network channel to request the latest fan equipment information. The data synchronization request contains fields such as the fan analyzer's identity information, current version number, and data type.

[0077] In some embodiments, the data synchronization mechanism of the wind turbine analyzer can be implemented in a variety of ways: Optionally, the wind turbine analyzer can adopt an incremental synchronization strategy, only requesting to obtain new or modified wind turbine information that is higher than the local version, reducing the amount of data transmission and synchronization time; Optionally, the wind turbine analyzer can also implement a regular automatic synchronization mechanism, actively checking and updating local wind turbine data at preset time intervals to ensure the timeliness of the data. It is understandable that other data synchronization strategies can also be used to ensure the accuracy of wind turbine information, which is not limited here.

[0078] S204, receiving the wind turbine incremental information returned by the cloud data center after verifying the current data version, and updating the wind turbine display list according to the wind turbine incremental information.

[0079] Among them, the wind turbine incremental information represents the new or updated wind turbine equipment information that is higher than the local version; data version verification refers to the cloud-based validity check of the local data version; the wind turbine display list is used to represent the list of wind turbine equipment available for selection on the wind turbine analyzer.

[0080] The fan analyzer waits for a response from the cloud after sending a data synchronization request. Specifically, when the cloud data center completes version verification, it will package and return the newly added or updated fan information. After receiving the incremental information, the fan analyzer first verifies the data integrity, then updates the valid data to the local database, and finally refreshes the device display interface so that users can see the latest fan list.

[0081] In some embodiments, the data update process of the wind turbine analyzer can be implemented in a variety of ways: Optionally, the wind turbine analyzer can implement an incremental update mechanism, first temporarily storing the incremental data, then comparing and merging it with the local data, and finally submitting it to the database to ensure the atomicity of the data update; Optionally, the wind turbine analyzer can also implement a data rollback mechanism, which can restore to the state before the update when an abnormality occurs during the update process to ensure data consistency. It is understandable that other data update strategies can also be used to ensure the reliable update of wind turbine information, which is not limited here.

[0082] S205. When the error identification code indicates that device authentication has failed, obtain the hardware serial number and security authentication key of the wind turbine analyzer.

[0083] Among them, the hardware serial number represents the factory unique identification code of the fan analyzer; the security authentication key refers to the encryption key used for device identity authentication.

[0084] The fan analyzer performs this step after receiving the error identification code indicating that the device authentication failed. Specifically, the fan analyzer first accesses the secure storage area of ​​the device and reads the hardware serial number written during the device manufacturing process. Then, it extracts the preset security authentication key from the encrypted storage module. This key is obtained through a secure channel and locally encrypted when the device is first activated. These two key parameters will be used in the subsequent device re-authentication process.

[0085] In some embodiments, the wind turbine analyzer can be implemented in a variety of ways to obtain security information: Optionally, the wind turbine analyzer can use a hardware security module to store key authentication information, and read the hardware serial number and key information through an independent encryption processor to provide a higher level of security protection; Optionally, the wind turbine analyzer can also implement a distributed key storage mechanism to store the authentication key in different storage areas, and reconstruct the complete authentication key through a specific key reorganization algorithm. It is understandable that other secure storage solutions can also be used to protect authentication information, which is not limited here.

[0086] S206: Encrypt the hardware serial number and the security authentication key based on a preset encryption algorithm to obtain a device authentication code, and send the device authentication code to the authentication server.

[0087] Among them, the preset encryption algorithm represents the cryptographic algorithm used to protect authentication information; the device authentication code refers to the device identity credential generated after processing by the encryption algorithm; the authentication server is used to represent a dedicated server responsible for device authorization authentication.

[0088] The wind turbine analyzer performs encryption processing after obtaining the security authentication information. Specifically, the wind turbine analyzer first combines the hardware serial number and the security authentication key in a predefined format to generate the original data block to be encrypted. Then, the data block is encrypted multiple times using a preset encryption algorithm, during which a random factor is introduced to increase the encryption strength. Finally, a device authentication code is generated and sent to the authentication server through a secure communication channel for verification.

[0089] In some embodiments, the authentication code generation process of the wind turbine analyzer can be implemented in a variety of ways: Optionally, the wind turbine analyzer can use a dynamic encryption mechanism based on timestamps, use the current time information as one of the encryption parameters, generate an authentication code with timeliness, and improve the security of the authentication process; Optionally, the wind turbine analyzer can also implement a multi-level encryption strategy, use encryption algorithms of different strengths for authentication information of different security levels, and balance security and performance requirements. It is understandable that other encryption schemes can also be used to generate device authentication codes, which are not limited here.

[0090] S207: Receive the device authorization authentication and device authorization time limit returned by the authentication server, and regenerate device identification information and detection request according to the device authorization authentication.

[0091] Among them, device authorization authentication refers to the legal device certificate issued by the authentication server; device authorization time limit refers to the validity period of the authentication; device identification information is used to indicate the device identity containing the authentication information.

[0092] After sending the authentication code, the fan analyzer waits for the response from the authentication server. Specifically, when the authentication server passes the verification, the fan analyzer will receive the response data containing the device authorization authentication and the authorization time limit. Then, based on the newly obtained authorization information, the fan analyzer regenerates the device identification information that meets the specifications and encapsulates it into a new detection request. This process ensures that subsequent data access requests carry valid authentication information.

[0093] Among them, the authorization update process of the wind turbine analyzer can adopt a multi-level security protection mechanism, the core of which is the identity authentication and data protection scheme based on asymmetric encryption. The system first uses the RSA algorithm to generate a unique public-private key pair for the device. The private key is stored in the device's security chip, and the public key is registered to the authentication server. The authorization update request is transmitted through a two-way authenticated TLS channel. The request data is signed with the device's private key and a random challenge code based on a timestamp is attached to prevent replay attacks. After the authentication server verifies the validity of the signature, it uses a dynamic key to encrypt the new authorization certificate. The key generation process uses the Diffie-Hellman key exchange protocol to ensure the forward security of the key. The authorization certificate contains information such as the device ID, authorization scope, and validity period, and is signed with the root certificate of the authentication center. To prevent the certificate from being illegally copied, the system adds binding information based on the hardware characteristics of the device to the certificate. For example, the CPU serial number, MAC address and other hardware parameters are hashed as part of the certificate to ensure that the certificate can only be used on a specific device. In addition, the system also implements a certificate revocation mechanism to prevent the continued use of revoked certificates through a regularly updated certificate revocation list (CRL).

[0094] S208, receiving the real-time vibration data, real-time displacement data and historical maintenance data of the target detection fan returned by the ventilation control system after successful authentication of the equipment identification information.

[0095] Referring to step S102 , the wind turbine analyzer receives real-time vibration data, real-time displacement data, and historical maintenance data.

[0096] S209: Calculate the vibration frequency domain signal based on the real-time vibration data, and perform spectrum analysis on the vibration frequency domain signal to determine the vibration spectrum characteristics of the target detection fan.

[0097] Referring to step S103 , the wind turbine analyzer determines the vibration spectrum characteristics of the target detection wind turbine.

[0098] S210, constructing an axis motion trajectory diagram based on the real-time displacement data, and performing trajectory feature analysis on the axis motion trajectory diagram to determine the axis trajectory features of the target detection fan.

[0099] Referring to step S104 , the fan analyzer determines the axis trajectory characteristics of the target detection fan.

[0100] S211. Input the vibration spectrum characteristics, axis trajectory characteristics and historical maintenance data into the operation evaluation model to obtain the operation status score of the target detection fan.

[0101] Referring to step S105 , the wind turbine analyzer determines the operating status score of the target detection wind turbine.

[0102] S212: Generate a maintenance recommendation report for the target detection fan based on the operation status score.

[0103] Referring to step S106, the fan analyzer generates a maintenance recommendation report.

[0104] In some embodiments, the fan analyzer will perform different report processing based on different operating status scores, that is, the operating status score is graded to determine the score range corresponding to the operating status score; the score range includes normal operating range, warning range and fault range; when the operating status score is in the warning range, the abnormal mode corresponding to the vibration spectrum characteristics and the axis trajectory characteristics is determined, and historical fault cases are matched according to the abnormal mode; based on historical fault cases, a maintenance recommendation report including fault warning information, maintenance suggestions and maintenance cycle suggestions is generated; when the operating status score is in the fault range, an emergency maintenance report including fault diagnosis results, maintenance plan and spare parts requirements is generated.

[0105] Among them, the operating status score is a quantitative indicator that reflects the current operating health of the equipment; the scoring range refers to the different level ranges for dividing the equipment status; the normal operating range represents the scoring range for the equipment to be in good operating condition, usually 80-100 points; the warning range represents the scoring range for the equipment to have early signs of failure, usually 60-80 points; the fault range is used to represent the scoring range for the equipment to have obvious failures, usually below 60 points; the abnormal mode refers to the characteristic performance of the equipment deviating from the normal working state; the historical failure cases are used to represent similar failure conditions that have been recorded and their handling methods.

[0106] The fan analyzer executes the report generation process after obtaining the operating status score. Specifically, the fan analyzer first compares the score value with the preset interval threshold to determine the interval type to which the current state belongs. When the score is in the warning interval, the system deeply analyzes the abnormal characteristics of the vibration and axis trajectory data, matches them with the fault characteristics in the historical case library through the pattern recognition algorithm, calculates the similarity score and extracts the case with the highest similarity as a reference. Based on the matched cases, the system generates an early warning report containing fault development trend predictions, recommended maintenance measures, and the optimal maintenance time window. When the score falls into the fault interval, the system immediately starts the fault diagnosis process, determines the specific fault type and location through feature analysis, and formulates a detailed maintenance plan based on the severity of the fault.

[0107] In some embodiments, the fan analyzer can also perform inspection planning, that is, the fan analyzer will obtain a maintenance report set and fan location information of multiple target detection fans; extract the fault severity, equipment importance and maintenance difficulty of multiple target detection fans in the maintenance report set, and determine the maintenance urgency index of multiple target detection fans; generate an inspection route based on the maintenance urgency index of multiple target detection fans, fan location information and inspection personnel information.

[0108] Among them, the maintenance report set represents a data set of maintenance and repair records of multiple fans; the fan location information refers to the geographical coordinates and spatial distribution data of each fan; the fault severity represents a quantitative indicator of the impact of equipment failure on system operation; the equipment importance is used to indicate the criticality of the fan in the entire system; the maintenance difficulty refers to the technical requirements and resource investment required to complete the maintenance work; the maintenance urgency index represents the degree of priority maintenance; the inspection path is used to indicate the optimal equipment inspection sequence and route planning.

[0109] The fan analyzer performs path planning when it is necessary to formulate an inspection plan. Specifically, the fan analyzer first extracts the maintenance report data of all target fans from the database and reads the spatial position coordinates of the fans. Then, based on the fault information in the maintenance report, the comprehensive evaluation index of each fan is calculated. During the calculation process, the system weights factors such as the severity of the fault, the importance of the equipment in production, and the technical difficulty required for maintenance to derive an emergency index that reflects the priority of maintenance. Finally, the system combines the spatial distribution of the fans and the skill level of the inspection personnel, and uses an optimization algorithm to generate the optimal inspection path to ensure that high-urgency equipment is given priority within a limited time.

[0110] Among them, the maintenance emergency index first constructs the equipment state vector: V = [v1, v2, ..., vn]; The state vector V contains n dimensions, which represent key indicators such as vibration amplitude ratio (ratio to the reference value), temperature change rate (percentage of temperature change per hour), shaft eccentricity (percentage relative to bearing clearance), and operating time ratio (percentage relative to design life).

[0111] Each indicator is mapped to a standard interval through a fuzzy membership function: μi(x)=1 / (1+exp(-k(xc))); the sensitivity coefficient k is set to 2.5 based on the statistical analysis of historical data, and the critical threshold c is determined by ROC curve analysis to be 1.5 times the standard deviation of the normal state of the equipment.

[0112] The time decay function expression is: I(t)=exp(-λ(t-t0)); where the attenuation coefficient λ is set to 0.05 / day, reflecting the time scale of fault development, and t0 is the initial observation time point.

[0113] The final emergency index calculation formula is: UI=Σ(wi·μi(vi))·I(t)·C(r); the equipment importance coefficient C(r) is a comprehensive assessment based on the equipment's position in the system, load level and backup status, and its value range is 0.1-1.0.

[0114] For example, the state vector V = [1.8, 2.5, 15, 85] of a fan indicates a vibration amplitude ratio of 1.8, a temperature change rate of 2.5% / hour, an axial eccentricity of 15%, and an operating time ratio of 85%. After fuzzy membership function mapping, we get: μ(V) = [0.85, 0.65, 0.45, 0.75]; 25 days have passed since the last maintenance of the fan, and the time decay function is substituted: I(25) = exp(-0.05×25) = 0.28; considering that the fan is located in the main ventilation path, its importance coefficient C(r) = 0.9. Using weight coefficient wi=[0.3, 0.25, 0.25, 0.2], substitute into the emergency index formula: UI=(0.3×0.85+0.25×0.65+0.25×0.45+0.2×0.75)×0.28×0.9=0.78; it ranks second among all the equipment to be repaired and needs to be repaired as a priority.

[0115] In some embodiments, an inspection path optimization model can be used to generate the optimal inspection path. The inspection path optimization model is trained using historical inspection records, equipment distribution data, and maintenance effect data. The training goal is to minimize the total inspection time while maximizing the timeliness of maintenance of high-risk equipment. The training criteria include indicators such as total path length, high-risk equipment coverage, and professional matching of personnel. The inspection path optimization model is based on an improved genetic algorithm, which models the inspection task as a multi-objective optimization problem. The model combines multiple constraints such as equipment location, maintenance urgency, maintenance difficulty, and personnel expertise to generate the optimal inspection path through iterative optimization. By inputting the location information of the current equipment to be inspected, the maintenance urgency index, and the available maintenance personnel information, the inspection path optimization model can calculate the optimal inspection path through an optimization algorithm, and output an inspection plan including maintenance sequence, personnel allocation, and estimated completion time.

[0116] S213: Obtain a repair status score of the target detection fan after maintenance.

[0117] Among them, the repair status score represents a quantitative indicator reflecting the status of the equipment after maintenance.

[0118] The fan analyzer performs a status assessment after the equipment has been overhauled. Specifically, the fan analyzer recollects the vibration and displacement data of the equipment, and uses the same feature extraction and evaluation methods as fault diagnosis to calculate the various performance indicators after the overhaul. These indicators are then compared with the standard status parameters, combined with the completion of the maintenance project, and finally a status score reflecting the maintenance effect is obtained.

[0119] In some embodiments, the maintenance evaluation process of the fan analyzer can be implemented in a variety of ways: Optionally, the fan analyzer can compare the changes in characteristic parameters before and after maintenance, calculate the degree of improvement of various indicators, and determine the scoring weight of the maintenance effect in combination with expert experience; Optionally, the fan analyzer can also establish a scoring model based on the type of equipment, and adopt differentiated scoring standards according to the characteristics of different types of equipment to improve the accuracy of the evaluation results. It is understandable that other evaluation methods can also be used to quantify the maintenance effect, which is not limited here.

[0120] S214. When the repair status score is higher than a preset acceptance threshold, a maintenance acceptance report including fault elimination verification is generated according to the operation status score and the repair status score.

[0121] Among them, the preset acceptance threshold represents the minimum score requirement for maintenance quality acceptance; fault elimination verification refers to the confirmation result of the fault elimination effect; and the maintenance acceptance report is used to represent the technical document that records the maintenance effect and acceptance conclusion.

[0122] After obtaining the repair status score, the fan analyzer performs an acceptance evaluation. Specifically, the repair status score is first compared with the preset acceptance threshold to confirm whether the repair quality meets the standard. When the score exceeds the threshold, the fan analyzer compares and analyzes the operating status score before the fault occurs and the repair status score after the repair to evaluate the improvement of the fault symptoms. Finally, based on the evaluation results, a complete acceptance report is generated that includes the fault handling process, repair effect verification, and follow-up suggestions.

[0123] Among them, the inspection and acceptance report can adopt a hierarchical and progressive information organization method, first recording the basic information of the equipment and the overview of the fault, including the time, type and impact of the fault. The core part is the maintenance effect evaluation. The system quantifies the maintenance effect by calculating the improvement rate of the characteristic parameters before and after the maintenance. The improvement rate calculation formula is: Improvement rate = (repair status score-fault status score) / (standard status score-fault status score)×100%.

[0124] At the same time, the system conducts time series analysis on various performance indicators and predicts the performance trend of the equipment through an exponential smoothing algorithm. The prediction model integrates influencing factors such as equipment operation time and load changes. For key performance indicators, the system also establishes a confidence interval to evaluate the stability of performance after maintenance. For example, when a fan bearing is replaced, the system will continuously monitor the vibration trend for 72 hours, and judge the reliability of the maintenance effect by comparing the relationship between the measured value and the confidence interval. The report finally gives maintenance suggestions and preventive measures based on data analysis to help operation and maintenance personnel formulate subsequent maintenance plans.

[0125] In some embodiments, when the repair status score is low, the fan analyzer will perform a secondary maintenance, that is, when the repair status score is not higher than a preset acceptance threshold, the test vibration data and test axis trajectory of the target detection fan at different speed gears are collected; based on the test vibration data and test axis trajectory, the remaining fault types of the target detection fan are determined; and a secondary maintenance recommendation is generated based on the remaining fault types.

[0126] Among them, secondary maintenance refers to the supplementary maintenance process after the initial maintenance effect fails to meet the standards; test vibration data refers to the equipment vibration signal collected at different speeds; the test axis trajectory is used to indicate the axis movement path under the test conditions; the remaining fault type refers to the equipment abnormality that still exists after maintenance; the secondary maintenance recommendation is used to indicate the specific maintenance plan for the remaining faults.

[0127] The fan analyzer starts the secondary maintenance process when it detects that the maintenance effect is not up to standard. Specifically, the fan analyzer first controls the equipment to run step by step according to the preset speed gear, and collects complete vibration data and axis trajectory data at each gear. Then the system performs multi-dimensional analysis on the collected data, including spectrum analysis, envelope analysis and trajectory feature extraction, and determines which abnormal features still exist through comparative analysis. Based on the identified abnormal features, the system further diagnoses the specific types and possible causes of the remaining faults, and finally generates a targeted secondary maintenance plan.

[0128] In the embodiment of the present application, due to the use of a data access mechanism based on equipment authentication, a multi-dimensional fault feature analysis method and an intelligent maintenance planning system, it is possible to achieve accurate evaluation of the wind turbine operating status and early warning of faults, effectively solving the problem that single vibration monitoring in traditional technology is difficult to detect potential faults in a timely manner and the scheduling efficiency of maintenance personnel is low, thereby realizing the transformation of equipment maintenance from passive response to active prevention. The accuracy of fault diagnosis is improved through the coordinated analysis of vibration spectrum and axis trajectory; the rational planning of maintenance work is achieved through scoring and grading and fault warning mechanisms; and the scheduling efficiency of maintenance resources is optimized through intelligent inspection path planning.

[0129] The fan analyzer in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a fan analyzer in an embodiment of the present application.

[0130] It should be noted that Figure 3 The structure of the wind turbine analyzer shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0131] like Figure 3 As shown, the wind turbine analyzer includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0132] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0133] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0134] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0136] Specifically, the fan analyzer of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the operation detection method of the tunnel fan provided in the above embodiment is implemented.

[0137] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the fan analyzer described in the above embodiment; or may exist independently without being assembled into the fan analyzer. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the fan analyzer, the fan analyzer implements the tunnel fan operation detection method provided in the above embodiment.

[0138] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0139] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0140] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for detecting the operation of a tunnel fan, characterized in that: Applied to a fan analyzer, the method comprises: Determine a target detection fan based on user settings, generate a detection request according to the device identification information of the fan analyzer and the target detection fan, and send the detection request to the ventilation control system; Receiving the real-time vibration data, real-time displacement data and historical maintenance data of the target detection fan returned by the ventilation control system after the device identification information is successfully authenticated; Calculating a vibration frequency domain signal based on the real-time vibration data, and performing spectrum analysis on the vibration frequency domain signal to determine the vibration spectrum characteristics of the target detection fan; Constructing an axis motion trajectory diagram based on the real-time displacement data, and performing trajectory feature analysis on the axis motion trajectory diagram to determine the axis trajectory features of the target detection fan; Inputting the vibration spectrum characteristics, the axis trajectory characteristics and the historical maintenance data into an operation evaluation model to obtain an operation status score of the target detection fan; Based on the operating status score, a maintenance recommendation report for the target detection wind turbine is generated.

2. The method according to claim 1, characterized in that After the steps of determining the target detection fan based on the user setting, generating a detection request according to the device identification information of the fan analyzer and the target detection fan, and sending the detection request to the ventilation control system, the method further includes: receiving an error identification code returned by the ventilation control system after authentication failure; When the error identification code indicates that the target detection wind turbine does not exist, a wind turbine data synchronization request including the current data version is sent to the cloud data center; Receive the wind turbine increment information returned by the cloud data center after verifying the current data version, and update the wind turbine display list according to the wind turbine increment information.

3. The method according to claim 2, characterized in that After the step of receiving the error identification code returned by the ventilation control system after authentication failure, the method further includes: When the error identification code indicates that device authentication has failed, obtaining the hardware serial number and security authentication key of the wind turbine analyzer; Encrypt the hardware serial number and the security authentication key based on a preset encryption algorithm to obtain a device authentication code, and send the device authentication code to an authentication server; Receive the device authorization authentication and device authorization time limit returned by the authentication server, and regenerate device identification information and detection request according to the device authorization authentication.

4. The method according to claim 1, characterized in that: The step of generating a maintenance recommendation report for the target detection fan based on the operating status score specifically includes: The operating status score is graded to determine a score interval corresponding to the operating status score; the score interval includes a normal operating interval, a warning interval, and a fault interval; When the operating status score is in the early warning interval, determining the abnormal mode corresponding to the vibration spectrum feature and the axis trajectory feature, and matching historical fault cases according to the abnormal mode; Based on the historical fault cases, a maintenance recommendation report including fault warning information, maintenance recommendations and repair cycle recommendations is generated; When the operating status score is in the fault range, an emergency maintenance report including a fault diagnosis result, a maintenance plan and spare parts requirements is generated.

5. The method according to claim 1, characterized in that After the step of generating a maintenance recommendation report for the target detection wind turbine based on the operating status score, the method further includes: Obtaining a repair status score of the target detection fan after maintenance; When the repair status score is higher than a preset acceptance threshold, a maintenance acceptance report including fault elimination verification is generated according to the operation status score and the repair status score.

6. The method according to claim 5, characterized in that After the step of obtaining the repair status score of the target detection wind turbine after overhaul, the method further includes: When the repair status score is not higher than a preset acceptance threshold, collecting test vibration data and test axis trajectory of the target detection fan at different speed gears; Determining the remaining fault type of the target detection fan based on the test vibration data and the test axis trajectory; A secondary maintenance suggestion is generated based on the remaining fault types.

7. The method according to claim 1, characterized in that After the step of generating a maintenance recommendation report for the target detection wind turbine based on the operating status score, the method further includes: Obtain maintenance report collection and fan location information of multiple target detection fans; Extracting the fault severity, equipment importance and maintenance difficulty of multiple target detection fans in the maintenance report set, and determining the maintenance urgency index of the multiple target detection fans; An inspection route is generated based on the maintenance urgency index of the wind turbine detected by the multiple targets, the wind turbine location information and the inspection personnel information.

8. A fan analyzer, characterized in that: The wind turbine analyzer includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the wind turbine analyzer to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a wind turbine analyzer, the wind turbine analyzer is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a wind turbine analyzer, the wind turbine analyzer is enabled to perform the method according to any one of claims 1 to 7.

Images