A tunnel fan monitoring method based on laser vibration measurement

Abstract

The present invention is a tunnel fan monitoring method based on laser vibration measurement, which relates to the field of computer processing technology and includes the following steps: S01, continuously acquiring blade trajectory data of the tunnel fan during operation using a laser detection instrument; S02, utilizing a laser rangefinder installed at a preset point on the tunnel fan to capture real-time image data of the blade motion; S03, employing an intelligent algorithm to analyze whether the blade trajectory data deviates from the normal range and to mark abnormal areas in the image data. By collecting and analyzing the trajectory data and image information of the tunnel fan blades in real time, this invention can promptly identify potential faults and problems, improving the accuracy and efficiency of monitoring. It can also enable remote monitoring and early warning of the tunnel fan's operating status, providing a scientific basis for tunnel fan maintenance and management, reducing maintenance costs, and improving tunnel safety and operational efficiency.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technology, and in particular to a tunnel fan monitoring method based on laser vibration measurement. Background Art

[0002] Ensuring the proper functioning of tunnel fans is crucial during tunnel operation and maintenance. Tunnel fans regulate air circulation within the tunnel, providing a safe environment for vehicles and pedestrians. However, due to long-term operation, environmental factors, and improper maintenance, tunnel fan blades may experience deformation and abnormal vibration. If these problems are not discovered and addressed promptly, they can lead to decreased tunnel fan performance or even failure, compromising the tunnel's ventilation and safety.

[0003] Traditional tunnel fan monitoring methods rely mainly on manual inspections and regular maintenance. This method has many shortcomings, such as:

[0004] Manual inspections require a lot of manpower and time, and may not detect potential faults in a timely manner;

[0005] Although regular maintenance can prevent some failures, the determination of maintenance cycles and projects often relies on experience and lacks scientificity and accuracy.

[0006] With the breakthrough development of laser precision detection technology and multimodal image recognition technology, the field of equipment operation status monitoring has ushered in a new opportunity for technological integration. By deeply coupling the laser scanning system with the intelligent image analysis module, the equipment operation trajectory data and multi-dimensional visual information can be simultaneously collected: on the one hand, laser point cloud scanning is used to accurately capture the deformation trajectory and vibration spectrum of the fan blades. On the other hand, characteristic images such as surface crack expansion and bolt loosening are obtained through industrial camera arrays. Finally, cross-validation of physical displacement data and visual feature parameters is achieved through spatiotemporal synchronization algorithms. In response to the health management needs of long-cycle operating equipment such as tunnel fans, how to build an intelligent monitoring system based on laser-visual fusion perception to achieve full-link health diagnosis from microscopic deformation monitoring to macroscopic status assessment has become a key technical bottleneck to ensure the safe operation of underground engineering ventilation systems, and urgently needs to be broken through through multi-source data fusion and status assessment model innovation. Summary of the Invention

[0007] In response to the above technical problems, the technical solution adopted by the present invention is a tunnel fan monitoring method based on laser vibration measurement, which includes the following steps:

[0008] S01. Continuously obtain blade trajectory data of the tunnel fan during operation using a laser detection instrument;

[0009] S02, using a laser rangefinder installed at a preset point on the tunnel fan to capture image data of the fan blade movement in real time;

[0010] S03, using an intelligent algorithm to analyze whether the blade trajectory data deviates from the normal range and mark the abnormal area in the image data, set monitoring points at the boundary of the abnormal area and calculate the maximum allowable deviation value AD of each monitoring point max ;

[0011] S04. Use a machine learning algorithm to calculate the expected deviation change rate and the deviation threshold ADpre of each monitoring point based on the historical operation log, and then obtain the actual deviation change rate DR based on the change of the fan blade trajectory data. now and Change Direction FX now ;

[0012] S05, when the actual deviation change rate DR is obtained now When the deviation threshold of the corresponding monitoring point is exceeded, the alarm mechanism is triggered;

[0013] S06. Record the deviation thresholds ADpre of the plurality of monitoring points and the working status of the tunnel fan, and store the monitoring results in a historical operation log.

[0014] Preferably, the camera installed at a preset point on the tunnel fan in step S01 includes:

[0015] The first laser rangefinder whose collecting end is coaxial with the axis of the fan blade of the tunnel fan is marked as S 1 ;

[0016] The second laser rangefinder with the axis of the acquisition end perpendicular to the axis of the fan blade of the tunnel fan is marked as S 2 ;

[0017] The third laser rangefinder, whose collection end axis is perpendicular to the collection end axis of the second laser rangefinder, is marked as S 3 .

[0018] Preferably, the step S03 of calculating the maximum allowable deviation value of each monitoring point includes:

[0019] S31, obtaining a coordinate sequence of the fan blade edge position in the image data, and using image processing technology to convert the coordinate sequence into a fan blade trajectory data image, and then using an edge detection algorithm to identify the fan blade edge, and connecting continuous edge points to form a fan blade outline;

[0020] S32. Extract the characteristic information of the fan blade contour through a convolutional neural network, compare it with the characteristics of the normal fan blade contour in the historical operation log, identify whether the fan blade deviates from the normal range, and mark the abnormal area.

[0021] As a preferred embodiment, S33, all monitoring records with similar abnormal area locations are screened out from the historical operation log, the blade trajectory data in the monitoring records of adjacent predetermined number of window periods are compared, and each trajectory is segmented according to the deviation direction and size, and the deviation value of each segment of the trajectory is calculated respectively, and the maximum value D with the largest deviation in all monitoring records is obtained. max The minimum value D with the smallest deviation min .

[0022] Preferably, the calculation of the maximum allowable deviation value of each monitoring point in step S03 further includes:

[0023] S34: Determine the relative position of the fan blade and the axis of the tunnel fan based on the fan blade trajectory data image, use the line connecting the fan blade edge and the axis of the tunnel fan as the baseline, calculate the offset angle and offset distance of the abnormal area relative to the baseline, and establish two points with an intersection angle of θ with the baseline, taking the points with the maximum offset angle and the farthest offset distance as endpoints. max On each straight line, find two lines perpendicular to the reference line at a distance equal to D. max As the vertex, a parallelogram area is divided according to the position of the four vertices as the first abnormal area; then two intersection angles of 180°-θ are established with the two end points as the midpoints. max And the straight lines are parallel to each other, and so on, a parallelogram area is divided again as the second abnormal area.

[0024] Preferably, the calculation of the maximum allowable deviation value of each monitoring point in step S03 further includes:

[0025] S35, merging the first abnormal area and the second abnormal area as an abnormal fusion area, and taking the overlapping area of the abnormal fusion area and the fan blade trajectory data image as the final abnormal area; evenly setting N monitoring points on the boundary line of the final abnormal area, respectively calculating the actual distance between each monitoring point and the axis of the tunnel fan, and then calculating the maximum allowable deviation value AD of each monitoring point based on the accuracy and measurement range of the laser rangefinder max .

[0026] Preferably, obtaining the actual deviation change rate and change direction in step S04 includes:

[0027] S41. Filter out all monitoring records with similar abnormal area locations in the historical operation log, count the number of these monitoring records V, and use the area of the abnormal area in each monitoring record as the independent variable, and use the average speed obtained by dividing the tunnel fan speed in each monitoring record by the abnormal duration as the dependent variable. Package the independent variable and the dependent variable in each monitoring record into samples, and package the V samples into a training set.

[0028] Preferably, obtaining the actual deviation change rate and change direction in step S04 includes:

[0029] S42. Substitute the training set into the linear regression model to obtain an expression after training. Then, obtain the area of the final abnormal region abnormalnow and substitute it into the expression to calculate the expected average speed. Then, based on the relationship between the tunnel fan speed and the blade trajectory data deviation, substitute it into the calculation to obtain the expected deviation change rate DRexp.

[0030] S43, calculate the maximum allowable deviation value AD of all monitoring points max The average value ADave, and then the maximum allowable deviation value AD of each monitoring point max Divide them by the expected deviation change rate DRexp to get the allowed time, and select the allowed time with the smallest value as the reaction time Treact.

[0031] Preferably, the deviation threshold ADpre of each monitoring point is calculated separately, and the formula is as follows: , for each monitoring point, the allowed duration for: , among which, AD max，i AD is the maximum allowable deviation value of the i-th monitoring point max， Select reaction time T react , , calculate the deviation threshold ADpre, ADpre,i=k×T react， Where i is a corresponding monitoring point and takes 1, 2, 3, ..., i, k is a constant and takes 5, and n is the total number of monitoring points;

[0032] S44, obtaining the coordinate data of the fan blade edge position in real time through a laser rangefinder, and calculating the actual deviation change rate DR by fitting a linear model based on the coordinate data now and Change Direction FX now .

[0033] As an example, in step S05, when the obtained deviation threshold ADpre exceeds the deviation threshold of the corresponding monitoring point, the actual deviation change rate DR obtained is obtained. nowCompare each monitoring point with the deviation threshold ADpre one by one, and adjust the value according to the change direction FX now Differ from the preset blade trajectory direction amplitude to obtain the deviation data FX p .

[0034] The present invention has at least the following beneficial effects:

[0035] 1. A laser rangefinder is used to capture real-time image data of fan blade movement, and an intelligent algorithm is used to analyze whether the fan blade trajectory data deviates from the normal range. Once an abnormality is found, an alarm mechanism is immediately triggered, thereby improving the safety and reliability of tunnel fan operation.

[0036] 2. It can accurately mark abnormal areas, set monitoring points at the boundaries of abnormal areas, and calculate the maximum allowable deviation value of each monitoring point, providing accurate data support for subsequent analysis and early warning.

[0037] 3. A machine learning algorithm is used to calculate the expected deviation change rate and the deviation threshold of each monitoring point based on historical operation logs, realizing the intelligent setting of the warning threshold and improving the accuracy and timeliness of the warning.

[0038] 4. The deviation thresholds of multiple monitoring points and the working status records of the tunnel fans are stored in the historical operation log to facilitate subsequent data analysis and problem tracing. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of a tunnel fan monitoring method based on laser vibration measurement provided in the first embodiment of the present invention;

[0041] Figure 2 This is a schematic diagram of the implementation structure of the laser rangefinder provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0043] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] Example 1:

[0045] This embodiment provides a tunnel fan monitoring method based on laser vibration measurement, which includes the following steps: Figure 1 As shown:

[0046] S01. Continuously obtain blade trajectory data of the tunnel fan during operation using a laser detection instrument;

[0047] S02, using a laser rangefinder installed at a preset point on the tunnel fan to capture image data of the fan blade movement in real time;

[0048] S03, using intelligent algorithms to analyze whether the fan blade trajectory data deviates from the normal range and mark the abnormal area in the image data, set monitoring points at the boundary of the abnormal area and calculate the maximum allowable deviation value AD of each monitoring point max ;

[0049] S04. Use machine learning algorithms to calculate the expected deviation change rate and the deviation threshold ADpre of each monitoring point based on the historical operation log, and then obtain the actual deviation change rate DR based on the change of the fan blade trajectory data. now and Change Direction FX now ;

[0050] S05, when the actual deviation change rate DR is obtained now When the deviation threshold of the corresponding monitoring point is exceeded, the alarm mechanism is triggered;

[0051] S06. Record the deviation thresholds ADpre of multiple monitoring points and the working status of the tunnel fan, and store the monitoring results in a historical operation log.

[0052] Specifically, the historical operation log in the above embodiment refers to monitoring records of the tunnel fan under different operating conditions. Each monitoring record includes the tunnel fan speed, blade trajectory data image, abnormal area location, and abnormality duration. The image data includes the maximum operating diameter of the blade edge position and the axial direction.

[0053] Further, combined Figure 2 As shown, in step S01 of the above embodiment, the cameras installed at preset points on the tunnel fan include:

[0054] The first laser rangefinder whose acquisition end is coaxial with the axis of the tunnel fan blade is marked as S 1 ;

[0055] The second laser rangefinder of the fan blade axis of the vertical tunnel fan at the acquisition end axis is marked as S 2 ;

[0056] The third laser rangefinder, whose collection end axis is perpendicular to the collection end axis of the second laser rangefinder, is marked as S 3 .

[0057] Specifically, the second and third laser rangefinders each acquire the radial displacement parameters of the fan blades in the operating state. The first laser rangefinder acquires both radial displacement parameters and circumferential parameters. Circumferential parameters refer to whether the rotation trajectory is a complete circle or a non-circular structure such as an ellipse. The radial displacement parameters acquired are the average of the values obtained by the first, second, and third laser rangefinders.

[0058] Secondly, the calculation of the maximum allowable deviation value of each monitoring point in step S03 in the above embodiment includes:

[0059] S31, obtaining a coordinate sequence of the fan blade edge position in the image data, and using image processing technology to convert the coordinate sequence into a fan blade trajectory data image, and then using an edge detection algorithm to identify the fan blade edge, and connecting continuous edge points to form a fan blade outline;

[0060] S32. Extracting feature information of the fan blade profile using a convolutional neural network, comparing it with features of normal fan blade profiles in historical operation logs, identifying whether the fan blade deviates from the normal range, and marking abnormal areas;

[0061] S33. Then, based on the historical operation log, all monitoring records with similar abnormal area locations are screened out, and the fan blade trajectory data in the monitoring records of the adjacent predetermined number of window periods are compared. Each trajectory is segmented according to the deviation direction and magnitude, and the deviation value of each segment of the trajectory is calculated respectively. The maximum value D of the largest deviation in all monitoring records is obtained.max The minimum value D with the smallest deviation min ;

[0062] S34. Determine the relative position of the fan blade and the tunnel fan axis based on the fan blade trajectory data image. Use the line connecting the fan blade edge and the tunnel fan axis as the baseline. Calculate the offset angle and offset distance of the abnormal area relative to the baseline. Use the point with the maximum offset angle and the farthest offset distance as the endpoint and establish two intersection angles θ with the baseline. max On each straight line, find two lines perpendicular to the reference line at a distance equal to D. max As the vertex, a parallelogram area is divided according to the position of the four vertices as the first abnormal area; then two intersection angles of 180°-θ are established with the two end points as the midpoints. max And the straight lines are parallel to each other, and so on, a parallelogram area is divided again as the second abnormal area;

[0063] S35, merging the first abnormal area and the second abnormal area as the abnormal fusion area, and taking the overlapping area of the abnormal fusion area and the fan blade trajectory data image as the final abnormal area; evenly setting N monitoring points on the boundary line of the final abnormal area, respectively calculating the actual distance between each monitoring point and the axis of the tunnel fan, and then calculating the maximum allowable deviation value AD of each monitoring point based on the accuracy and measurement range of the laser rangefinder max .

[0064] Specifically, first identify whether the fan blades deviate from the normal range and mark the abnormal area, then divide the abnormal area according to the historical operation log and the operation trajectory of the fan blades and calculate the maximum allowable deviation value of each monitoring point. That is, a "safety range" is set on the movement trajectory of the fan blades, and an alarm will be triggered once this range is exceeded. This provides necessary data support for the implementation of step S03 using an intelligent algorithm to analyze whether the fan blade trajectory data deviates from the normal range and mark the abnormal area in the image data, and step S05 triggering the alarm mechanism when the actual deviation change rate obtained exceeds the deviation threshold of the corresponding monitoring point. This achieves the accurate determination of the maximum allowable deviation value of each monitoring point, providing a reliable basis for subsequent deviation monitoring and alarming.

[0065] Furthermore, in step S04 of the above embodiment, obtaining the actual deviation change rate and change direction includes:

[0066] S41. Filter all monitoring records with similar abnormal area locations in the historical operation log, count the number of these monitoring records (V), use the area of the abnormal area in each monitoring record as the independent variable, and divide the tunnel fan speed in each monitoring record by the abnormal duration to obtain the average speed as the dependent variable. Package the independent variable and the dependent variable in each monitoring record into samples, and package V samples into a training set.

[0067] S42. Substitute the training set into the linear regression model to obtain an expression after training. Then, obtain the area of the final abnormal region abnormalnow and substitute it into the expression to calculate the expected average speed. Then, based on the relationship between the tunnel fan speed and the blade trajectory data deviation, substitute it into the calculation to obtain the expected deviation change rate DRexp.

[0068] S43, calculate the maximum allowable deviation value AD of all monitoring points max The average value ADave, and the maximum allowable deviation value AD of each monitoring point max Divide each by the expected deviation change rate DRexp to obtain the allowed time, select the minimum allowed time as the reaction time Treact, and calculate the deviation threshold ADpre for each monitoring point. The formula is as follows:

[0069] ,

[0070] For each monitoring point, the allowed duration for:

[0071] ,

[0072] Among them, AD max，i AD is the maximum allowable deviation value of the i-th monitoring point max， Select reaction time T react，

[0073] ,

[0074] Calculate the deviation threshold ADpre, , where i is a corresponding monitoring point and takes 1, 2, 3, ..., i, k is a constant and takes 5, and n is the total number of monitoring points;

[0075] S44, using a laser rangefinder to obtain the coordinate data of the fan blade edge position in real time, and using the linear model to fit the coordinate data to obtain the actual deviation change rate DR now and Change Direction FX now .

[0076] In the above embodiment, similar monitoring records from historical operation logs are filtered and packaged into a training set. This is then substituted into a linear regression model for training to obtain an expression. The predicted average rotational speed and predicted deviation change rate are then calculated based on the area of the current abnormal region. Finally, the deviation threshold is calculated based on the maximum allowable deviation value and predicted deviation change rate at each monitoring point. Furthermore, through machine learning algorithms and real-time data analysis, the future deviation trend of the fan blades can be predicted, and an alarm can be triggered promptly when the deviation exceeds the threshold, thereby improving the monitoring system's early warning capabilities and response speed.

[0077] Furthermore, in step S05, when the obtained deviation threshold ADpre exceeds the deviation threshold of the corresponding monitoring point, the actual deviation change rate DR now Compare each monitoring point with the deviation threshold ADpre one by one, and adjust the value according to the change direction FX now Differ from the preset blade trajectory direction amplitude to obtain the deviation data FX p .

[0078] The above comparison and calculation can more accurately determine whether the fan blade movement state is abnormal, and provide more useful information for subsequent troubleshooting and repair. At the same time, this also further strengthens the monitoring system's alarm mechanism, enabling it to respond to abnormal situations in a timely manner and take appropriate measures.

[0079] The first embodiment of the present invention uses a laser rangefinder to capture the image data of the fan blade movement in real time, and uses an intelligent algorithm to analyze whether the fan blade trajectory data deviates from the normal range. Once an abnormality is found, the alarm mechanism is immediately triggered, thereby improving the safety and reliability of the tunnel fan operation. Secondly, it can accurately mark the abnormal area, set monitoring points at the boundary of the abnormal area, calculate the maximum allowable deviation value of each monitoring point, and provide accurate data support for subsequent analysis and early warning. Furthermore, a machine learning algorithm is used to calculate the expected deviation change rate and the deviation threshold of each monitoring point based on the historical operation log, realizing the intelligent setting of the early warning threshold and improving the accuracy and timeliness of the early warning. In addition, the deviation thresholds of multiple monitoring points and the working status of the tunnel fan are recorded and stored in the historical operation log to facilitate subsequent data analysis and problem tracing.

[0080] Example 2:

[0081] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the steps:

[0082] Laser detection equipment is used to continuously obtain blade trajectory data of tunnel fans during operation;

[0083] Use laser rangefinders installed at preset points on tunnel fans to capture image data of fan blade movement in real time;

[0084] An intelligent algorithm is used to analyze whether the blade trajectory data deviates from the normal range and mark the abnormal area in the image data. Monitoring points are set at the boundaries of the abnormal area and the maximum allowable deviation value AD of each monitoring point is calculated. max ;

[0085] The machine learning algorithm is used to calculate the expected deviation change rate and the deviation threshold ADpre of each monitoring point based on the historical operation log, and then the actual deviation change rate DR is obtained according to the change of the fan blade trajectory data. now and Change Direction FX now ;

[0086] When the actual deviation change rate DR is obtained now When the deviation threshold of the corresponding monitoring point is exceeded, the alarm mechanism is triggered;

[0087] The deviation thresholds ADpre of multiple monitoring points and the working status of the tunnel fan are recorded and stored in the historical operation log.

[0088] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0089] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0090] Example 3:

[0091] An embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the following steps:

[0092] Laser detection equipment is used to continuously obtain blade trajectory data of tunnel fans during operation;

[0093] Use laser rangefinders installed at preset points on tunnel fans to capture image data of fan blade movement in real time;

[0094] An intelligent algorithm is used to analyze whether the blade trajectory data deviates from the normal range and mark the abnormal area in the image data. Monitoring points are set at the boundaries of the abnormal area and the maximum allowable deviation value AD of each monitoring point is calculated. max ;

[0095] The machine learning algorithm is used to calculate the expected deviation change rate and the deviation threshold ADpre of each monitoring point based on the historical operation log, and then the actual deviation change rate DR is obtained according to the change of the fan blade trajectory data. now and Change Direction FX now ;

[0096] When the actual deviation change rate DR is obtained now When the deviation threshold of the corresponding monitoring point is exceeded, the alarm mechanism is triggered;

[0097] The deviation thresholds ADpre of multiple monitoring points and the working status of the tunnel fan are recorded and stored in the historical operation log.

[0098] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any technician familiar with the present profession can make some changes or modifications to equivalent embodiments of the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A tunnel fan monitoring method based on laser vibration measurement, characterized in that: The method comprises the following steps: S01. Continuously obtain blade trajectory data of the tunnel fan during operation using a laser detection instrument; S02, using a laser rangefinder installed at a preset point on the tunnel fan to capture image data of the fan blade movement in real time; S03, using an intelligent algorithm to analyze whether the blade trajectory data deviates from the normal range and mark the abnormal area in the image data, set monitoring points at the boundary of the abnormal area and calculate the maximum allowable deviation value AD of each monitoring point max ; S04. Use a machine learning algorithm to calculate the expected deviation change rate and the deviation threshold ADpre of each monitoring point based on the historical operation log, and then obtain the actual deviation change rate DR based on the change of the fan blade trajectory data. now and Change Direction FX now ; S05, when the actual deviation change rate DR is obtained now When the deviation threshold of the corresponding monitoring point is exceeded, the alarm mechanism is triggered; S06, recording the deviation thresholds ADpre of the plurality of monitoring points and the working status of the tunnel fan, and storing the monitoring results in a historical operation log; The calculation of the maximum allowable deviation value of each monitoring point in step S03 further includes: S35, merging the first abnormal area and the second abnormal area as an abnormal fusion area, and taking the overlapping area of the abnormal fusion area and the fan blade trajectory data image as the final abnormal area; evenly setting N monitoring points on the boundary line of the final abnormal area, respectively calculating the actual distance between each monitoring point and the axis of the tunnel fan, and then calculating the maximum allowable deviation value AD of each monitoring point based on the accuracy and measurement range of the laser rangefinder max ; Obtaining the actual deviation change rate and change direction in step S04 includes: S42. Substitute the training set into the linear regression model to obtain an expression after training. Then, obtain the area of the final abnormal region abnormalnow and substitute it into the expression to calculate the expected average speed. Then, based on the relationship between the tunnel fan speed and the blade trajectory data deviation, substitute it into the calculation to obtain the expected deviation change rate DRexp. S43, calculate the maximum allowable deviation value AD of all monitoring points max The average value ADave, and then the maximum allowable deviation value AD of each monitoring point max Divide them by the expected deviation change rate DRexp to get the allowed time, and select the allowed time with the smallest value as the reaction time Treact; The deviation threshold ADpre of each monitoring point is calculated separately, and the formula is as follows: ， For each monitoring point, the allowed duration for: ， Among them, AD max，i AD is the maximum allowable deviation value of the i-th monitoring point max， Select reaction time T react , ， Calculate the deviation threshold ADpre, ， Where i is a corresponding monitoring point and takes 1, 2, 3, ..., i, k is a constant and takes 5, and n is the total number of monitoring points; S44, obtaining the coordinate data of the fan blade edge position in real time through a laser rangefinder, and calculating the actual deviation change rate DR by fitting a linear model based on the coordinate data now and Change Direction FX now .

2. The tunnel fan monitoring method based on laser vibration measurement according to claim 1 is characterized in that: The cameras installed at preset points on the tunnel fan in step S01 include: The first laser rangefinder whose collecting end is coaxial with the axis of the fan blade of the tunnel fan is marked as S 1 ; The second laser rangefinder with the axis of the acquisition end perpendicular to the axis of the fan blade of the tunnel fan is marked as S 2 ; The third laser rangefinder, whose collection end axis is perpendicular to the collection end axis of the second laser rangefinder, is marked as S 3 .

3. The tunnel fan monitoring method based on laser vibration measurement according to claim 1 is characterized in that: The step S03 of calculating the maximum allowable deviation value of each monitoring point includes: S31, obtaining a coordinate sequence of the fan blade edge position in the image data, and using image processing technology to convert the coordinate sequence into a fan blade trajectory data image, and then using an edge detection algorithm to identify the fan blade edge, and connecting continuous edge points to form a fan blade outline; S32. Extract the characteristic information of the fan blade contour through a convolutional neural network, compare it with the characteristics of the normal fan blade contour in the historical operation log, identify whether the fan blade deviates from the normal range, and mark the abnormal area.

4. The tunnel fan monitoring method based on laser vibration measurement according to claim 3 is characterized in that: The calculation of the maximum allowable deviation value of each monitoring point in step S03 further includes: S33, filtering out all monitoring records with similar abnormal area locations from the historical operation log, comparing the fan blade trajectory data in the monitoring records of adjacent predetermined number of window periods, and segmenting each trajectory according to the deviation direction and size, respectively calculating the deviation value of each segment of the trajectory, and obtaining the maximum value D with the largest deviation in all monitoring records. max The minimum value D with the smallest deviation min .

5. The tunnel fan monitoring method based on laser vibration measurement according to claim 4 is characterized in that: The calculation of the maximum allowable deviation value of each monitoring point in step S03 further includes: S34: Determine the relative position of the fan blade and the axis of the tunnel fan based on the fan blade trajectory data image, use the line connecting the fan blade edge and the axis of the tunnel fan as the baseline, calculate the offset angle and offset distance of the abnormal area relative to the baseline, and establish two points with an intersection angle of θ with the baseline, taking the points with the maximum offset angle and the farthest offset distance as endpoints. max On each straight line, find two lines perpendicular to the reference line at a distance equal to D. max As the vertex, a parallelogram area is divided according to the position of the four vertices as the first abnormal area; then two intersection angles with the baseline are established with the two end points as the midpoints. And the straight lines are parallel to each other, and so on, a parallelogram area is divided again as the second abnormal area.

6. The tunnel fan monitoring method based on laser vibration measurement according to claim 1 is characterized in that: Obtaining the actual deviation change rate and change direction in step S04 includes: S41. Filter out all monitoring records with similar abnormal area locations in the historical operation log, count the number of these monitoring records V, and use the area of the abnormal area in each monitoring record as the independent variable, and use the average speed obtained by dividing the tunnel fan speed in each monitoring record by the abnormal duration as the dependent variable. Package the independent variable and the dependent variable in each monitoring record into samples, and package the V samples into a training set.

7. The tunnel fan monitoring method based on laser vibration measurement according to claim 1 is characterized in that: In step S05, when the obtained deviation threshold ADpre exceeds the deviation threshold of the corresponding monitoring point, the actual deviation change rate DR now Compare each monitoring point with the deviation threshold ADpre one by one, and adjust the value according to the change direction FX now Differ from the preset blade trajectory direction amplitude to obtain the deviation data FX p .

Images