A tower crane damage prevention intelligent detection system and method based on big data

Abstract

The invention discloses a tower crane damage prevention intelligent detection system and method based on big data, belonging to the field of damage prevention intelligent detection technology. A three-dimensional model of a tower body is generated by three-dimensional modeling software; real-time related data of the tower body of the tower crane is monitored, and the central processing system is used to determine whether the tower body of the current tower crane is damaged, and the damage of the tower body is promptly processed according to the damage determination result of the current tower body; a damage prevention detection model is constructed according to the tower body related data in a non-damaged state and the related data of each time node of the tower body obtained by monitoring, and the real-time related data of the tower body is analyzed by the damage prevention detection model, and the tower body damage risk is predicted, and the risk factors of the tower body are located according to the prediction results, and the tower body is damaged according to the location of the risk factors of the tower body. The safe operation of the tower crane and the safety of personnel at the construction site are ensured, the damage of the tower body is prevented, and the service life of the tower crane is extended.

Description

Technical Field

[0001] The present invention relates to the technical field of damage prevention intelligent detection technology, and specifically to a tower crane damage prevention intelligent detection system and method based on big data. Background Art

[0002] Tower cranes, also known as tower cranes, are one of the key mechanical equipment in modern construction. They are mainly used for vertical transportation of materials and component installation in multi-story and high-rise building construction. Tower cranes need to perform a large number of heavy loads and braking operations during operation, which have a strong impact on the tower crane structure. The conventional height of tower cranes has reached more than 100 meters. As the service time of tower cranes increases, the micro-damage increases, making the tower cranes at risk of collapse.

[0003] Therefore, detecting the damage of tower cranes is crucial to the safety of construction sites. In order to ensure the safe operation of tower cranes, guarantee the progress of engineering construction, and achieve early identification and early intervention before accidents occur, the present invention provides a tower crane damage prevention intelligent detection system and method based on big data. Summary of the invention

[0004] The purpose of the present invention is to provide a tower crane damage prevention intelligent detection system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a tower crane damage prevention intelligent detection method based on big data, the method comprising the following steps:

[0006] S1: Obtain the tower crane's tower body related data in an undamaged state, and generate a 3D model of the tower body through 3D modeling software; the 3D model of the tower body will be used for subsequent structural analysis, damage detection, maintenance planning and other applications.

[0007] S2: Monitor the real-time data of the tower crane and determine whether the tower crane is damaged through the central processing system;

[0008] S3: A damage prevention detection model is constructed based on the tower body related data in an undamaged state and the tower body related data at each time node obtained through monitoring. The real-time tower body related data is analyzed through the damage prevention detection model to predict the tower body damage risk;

[0009] S4: Process the damage of the tower body according to the damage identification result of the current tower body in S2, locate the risk factors of the tower body according to the prediction result of the damage risk of the tower body in S3, and perform damage prevention treatment on the tower body according to the location of the risk factors of the tower body.

[0010] Furthermore, the S1 comprises the following steps:

[0011] S1-1: Measure the relevant data of each standard section of the tower body in an undamaged state, including sensor detection values, geometric parameters and material characteristic parameters; use three-dimensional measurement technology, such as laser scanning or photogrammetry, to obtain the spatial position point coordinate information of each standard section of the tower body, and store the obtained information in the database; these coordinate data will be used to generate a three-dimensional model of the tower body.

[0012] S1-2: Import the collected data into the 3D modeling software, and use the modeling tools of the software to generate a 3D model of the tower body according to the coordinates of the spatial position points;

[0013] S1-3: Extract the spatial position point coordinate set of the tower body according to the three-dimensional model of the tower body, denoted as P = {P i |i∈[1,n]}, where n represents the total number of spatial position coordinates of the tower, P i Represents the coordinates of the i-th spatial position point, including the coordinate values ​​in the x, y, and z directions, P i =(x i ,y i , z i ), where the x direction represents the east-west direction, the y direction represents the north-south direction, and the z direction represents the vertical direction;

[0014] Further, the S2 comprises the following steps:

[0015] S2-1: By installing sensors at the standard sections and connectors of the tower, the data collected by the sensors covers the tower, so as to comprehensively detect the status of the tower; monitor the real-time relevant data of the tower, including the stress, vibration frequency, displacement and other data of the tower;

[0016] S2-2: Establish a central processing system, which is used to store, process and analyze real-time data; transmit the real-time relevant data of the tower body monitored by the sensor to the central processing system, and the central processing system stores the received real-time relevant data and performs data preprocessing to form a first detection data set, which is recorded as F t ={C j |j∈[1,J]}, where F t represents the first detection data set at the tth time node, C j represents the real-time monitoring value uploaded by the jth sensor, and J represents the total number of sensors;

[0017] S2-3: Analyze the damage status of the tower body of the current tower crane through the central processing system, match the first detection data set with the first detection standard data set stored in the database, and determine whether the current tower body is damaged; the first detection standard data set is recorded as F f = {B j |j∈[1,J]},Bj represents the corresponding detection value of the jth sensor in the non-destructive state; the matching degree D between the first detection data set and the first detection standard data set at the tth time node is calculated according to the following formula t :

[0018]

[0019] When D t = 0, it is determined that the tower body has no damage; when D t When the standard difference value d preset in the database is exceeded, it is determined that the tower body at the tth time node is damaged; when D t does not exceed the standard difference value d preset in the database, and D t When the value is greater than 0, the tower body shall be inspected for damage prevention;

[0020] Further, the S3 comprises the following steps:

[0021] S3-1: Based on the data set in the undamaged state, a damage prevention detection model is constructed, including the following steps:

[0022] S3-1-1: Combine the three-dimensional model of the tower body and mark the coordinates of the sensor position in the spatial position point coordinate set of the tower body to generate the spatial position point coordinate set of the sensor, denoted as Q = {Q j |j∈[1,J]}, where Q j represents the coordinates of the jth marked spatial position point, Q j =(x j ,y j , z j ); According to the coordinates of the sensor, select the reference point, assume that there is a dependency relationship between the sensors in the same plane in the z direction, and record the set of sensors with a dependency relationship as L = {L k |k∈[1,δ]}, where L k represents the kth group of sensor sets with dependent relationships, δ represents the number of sensor sets with dependent relationships, δ≤J;

[0023] S3-1-2: Calculate the risk value G(r) of the rth standard section of the tower body according to the following formula:

[0024]

[0025] Where r∈[1,R], R represents the number of standard sections of the tower; J r represents the total number of sensors on the rth standard section of the tower, δ r represents the total number of sensor sets with dependencies on the rth standard section of the tower; ω1 and ω2 represent influence coefficients, which are preset by relevant personnel;

[0026] The tower body of the tower crane is composed of multiple standard sections. According to the structural characteristics of the tower body, the above formula can eliminate the detection error of the single sensor, perform layered detection on each standard section of the tower body, and analyze the overall status of the standard section in combination with the detection data of the single sensor. The potential risks of the standard section are identified, and then the risk factors are located, avoiding actual damage to the standard section and preventing the tower body from collapsing.

[0027] S3-1-3: define the initial accumulator sum and initialize it to 0, import the formula G(r), when G(r) receives the input value, it returns an updated output value Y, define the independent variable sequence, including a series of independent variable values; input the data of each standard section in the second detection data set into the formula G(r), calculate G(r) to obtain the output value Y, and then update the accumulator sum, sum=sum+Y; when all the standard sections of the tower body are input, the last updated sum value is used as the detection value output by the model;

[0028] Through the above steps, each standard section of the tower body can be inspected in turn, and the damage risk of the tower body can be judged by accumulating the size of the risk value, and further the real-time status loss prevention detection of the entire tower body can be realized.

[0029] S3-2: Based on the first detection data set in step S2, combined with the three-dimensional model of the tower body, a second detection data set is formed, wherein the second detection data set includes real-time relevant data of each standard section of the tower body;

[0030] S3-3: Input the second detection data set into the damage prevention detection model, and detect each standard section of the tower crane tower body through the damage prevention detection model. When the detection value output by the damage prevention detection model is less than R, it is determined that there is a damage risk to the current tower body; when the detection value output by the damage prevention detection model is greater than or equal to R, and the risk value of each standard section of the tower body is greater than or equal to 1, it is determined that there is no damage risk to the current tower body.

[0031] Further, the S4 comprises the following steps:

[0032] S4-1: Obtain the damage identification result of the current tower body in S2. When it is determined that the tower body is damaged, verify the type and degree of the damage through non-destructive testing technology, determine the impact of the damage on the performance and construction safety of the tower crane, and formulate a corresponding maintenance plan according to the type and degree of the damage, including measures such as repairing and replacing damaged parts and strengthening structural support; perform necessary maintenance and replacement of the tower body according to the maintenance plan;

[0033] S4-2: Obtain the prediction result of the tower damage risk in S3, and when it is determined that the current tower has a damage risk, locate the risk factors of the tower;

[0034] When G(r) < 1, it is determined that the rth standard section of the tower contains risk factors, and the rth standard section is marked for risk, and the specific spatial position of the standard section containing risk factors is located. When the tower crane is climbing, the operating parameters of the climbing mechanism within the rth standard section of the tower are adjusted to reduce the risk of damage.

[0035] S4-3: Issue a warning signal, report the specific spatial location information of the standard section containing risk elements, and provide feedback to relevant management personnel.

[0036] A tower crane damage prevention intelligent detection system based on big data, the system comprising: a tower crane data acquisition module, a tower crane data monitoring module, a damage prevention intelligent detection module and a damage management module;

[0037] The tower crane data acquisition module is used to collect tower crane tower body related data, and build a tower body three-dimensional model based on the collected data, and store the tower body related data in a non-destructive state in a database;

[0038] The tower crane data monitoring module is used to monitor the real-time tower crane tower body related data, determine whether the tower body is damaged, and process the tower body related data collected at each time node;

[0039] The damage prevention intelligent detection module is used to detect the tower body state through the damage prevention detection model, predict the damage risk of the tower body, and transmit the prediction result to the damage state management module;

[0040] The damage management module is used to process the monitored tower body damage, locate the risk factors of the tower body, and perform damage prevention processing on the tower body according to the location of the risk factors of the tower body.

[0041] Furthermore, the tower crane data acquisition module includes a tower model building unit and a lossless state data acquisition unit;

[0042] The tower body model building unit is used to collect tower body related data of the tower crane and generate a three-dimensional model of the tower body through three-dimensional modeling software;

[0043] The damage-free state data acquisition unit is used to acquire the relevant data of the tower body in the damage-free state, and upload and store the acquired data in a database.

[0044] Furthermore, the tower crane data monitoring module includes a tower body data acquisition unit, a tower body damage identification unit and a tower body data processing unit;

[0045] The tower body data acquisition unit is used to collect real-time relevant data of the tower body;

[0046] The tower body damage identification unit is used to identify the damage of the tower body according to the real-time data of the tower body;

[0047] The tower body data processing unit is used to process the real-time tower body related data collected by the tower body data collection unit, and mark the coordinates of the sensor position in the tower body spatial position point coordinate set in combination with the tower body three-dimensional model to generate the sensor spatial position point coordinate set, denoted as Q = {Q j |j∈[1,J]}, where Q j represents the coordinates of the jth marked spatial position point, Q j =(x j ,y j , z j ); According to the coordinates of the sensor, select the reference point, assume that there is a dependency relationship between the sensors in the same plane in the z direction, and record the set of sensors with a dependency relationship as L = {L k |k∈[1,δ]}, where L k represents the kth group of sensor sets with dependent relationships, δ represents the number of sensor sets with dependent relationships, δ≤J; the processed data is transmitted to the loss prevention intelligent detection module.

[0048] Furthermore, the loss prevention intelligent detection module includes a loss prevention detection model building unit, a loss prevention detection unit and an intelligent feedback unit;

[0049] The damage prevention detection model construction unit is used to construct a damage prevention detection model according to the data transmitted by the tower body data processing unit; the damage prevention detection model includes an accumulator sum and an import formula G(r), wherein the risk value G(r) of the rth standard section of the tower body is calculated according to the following formula:

[0050]

[0051] Where r∈[1,R], R represents the number of standard sections of the tower; J r represents the total number of sensors on the rth standard section of the tower, δ r represents the total number of sensor sets with dependencies on the rth standard section of the tower; ω1 and ω2 represent influence coefficients, which are preset by relevant personnel;

[0052] The anti-damage detection unit is used to detect the tower body through the anti-damage detection model according to the real-time relevant data of the tower body, input the data of each standard section in the second detection data set into the formula G(r), calculate G(r) to obtain the output value, and then update the accumulator sum; when all the standard sections of the tower body are input, the last updated sum value is used as the detection value output by the model; and the damage risk of the tower body is predicted by the value of the detection value;

[0053] The intelligent feedback unit is used to provide feedback on the tower body condition according to the prediction result of the damage prevention detection unit, and transmit the prediction result to the damage status management module.

[0054] Further, the damage management module includes a damage prevention and positioning unit and a damage management unit;

[0055] The anti-damage positioning unit is used to locate the risk factors of the tower body according to the feedback of the intelligent feedback unit, so as to take timely measures to prevent the tower body from being damaged;

[0056] The damage management unit is used to process the damage of the tower body according to the judgment result of the tower body damage judgment unit, and to perform damage prevention on the tower body according to the risk factor positioning of the tower body. Through accurate damage treatment and preventive maintenance, maintenance costs can be optimized, unnecessary repairs and replacements can be avoided, and the long-term reliability of key components can be ensured.

[0057] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0058] By monitoring the real-time status of the tower crane and detecting the damage of the tower crane, the damage to the tower crane body can be quickly located, ensuring the safe operation of the tower crane and the safety of personnel on the construction site, improving operational efficiency, and ensuring that the work progress of the construction team is not affected.

[0059] Through real-time monitoring and predictive maintenance, the operating efficiency of tower cranes can be improved and downtime caused by maintenance and failures can be reduced. By collecting real-time data on the tower crane body, a damage prevention detection model is built to detect the tower body, predict the damage risk of the tower body, and prevent damage from occurring, providing a more reliable, efficient, and safer operating environment for construction projects.

[0060] By building a damage prevention detection model and locating risk factors, we can more effectively manage the risks in the tower crane operation process and improve the overall safety of the construction project. By adjusting the use strategy of the tower standard section, the wear of the tower standard section is reduced and the service life of the tower crane is extended. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0062] Figure 1 It is a structural schematic diagram of a tower crane damage prevention intelligent detection system based on big data of the present invention;

[0063] Figure 2 It is a flow chart of a tower crane damage prevention intelligent detection method based on big data according to the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] See also Figure 1 , in the first embodiment: a tower crane damage prevention intelligent detection system based on big data is provided, comprising: a tower crane data acquisition module, a tower crane data monitoring module, a damage prevention intelligent detection module and a damage management module;

[0066] The tower crane data acquisition module is used to collect tower crane tower body related data, build a tower body three-dimensional model based on the collected data, and store the tower body related data in a non-destructive state in a database; it includes a tower body model building unit and a non-destructive state data acquisition unit;

[0067] The tower model construction unit is used to collect tower body related data of the tower crane and generate a three-dimensional model of the tower body through three-dimensional modeling software; the lossless state data acquisition unit is used to acquire tower body related data in an undamaged state and upload and store the acquired data in a database.

[0068] The tower crane data monitoring module is used to monitor the real-time tower crane tower data, determine whether the tower is damaged, and process the tower data collected at each time point; it includes a tower data collection unit, a tower damage determination unit, and a tower data processing unit;

[0069] The tower body data acquisition unit is used to collect real-time relevant data of the tower body; the tower body damage judgment unit is used to judge the damage of the tower body according to the real-time data of the tower body; the tower body data processing unit is used to process the real-time relevant data of the tower body collected by the tower body data acquisition unit, and transmit the processed data to the loss prevention intelligent detection module.

[0070] The damage prevention intelligent detection module is used to detect the tower body state through the damage prevention detection model, predict the damage risk of the tower body, and transmit the prediction result to the damage state management module; it includes a damage prevention detection model construction unit, a damage prevention detection unit and an intelligent feedback unit;

[0071] The damage prevention detection model construction unit is used to construct a damage prevention detection model based on the data transmitted by the tower body data processing unit; the damage prevention detection unit is used to detect the tower body through the damage prevention detection model according to the real-time relevant data of the tower body, and predict the damage risk of the tower body; the intelligent feedback unit is used to provide feedback on the tower body condition according to the prediction result of the damage prevention detection unit, and transmit the prediction result to the damage status management module.

[0072] The damage management module is used to process the monitored tower damage, locate the risk factors of the tower, and perform damage prevention on the tower according to the location of the risk factors of the tower; it includes a damage prevention positioning unit and a damage management unit;

[0073] The anti-damage positioning unit is used to locate the risk factors of the tower body according to the feedback from the intelligent feedback unit to prevent damage to the tower body; the damage management unit is used to process the damage to the tower body according to the judgment result of the tower damage judgment unit, and to perform anti-damage treatment on the tower body according to the positioning of the risk factors of the tower body.

[0074] See also Figure 2 In the second embodiment, a tower crane damage prevention intelligent detection method based on big data is provided, comprising the following steps:

[0075] S1: Obtain the tower crane's tower body related data in an undamaged state, and generate a 3D model of the tower body through 3D modeling software; the 3D model of the tower body will be used for subsequent structural analysis, damage detection, maintenance planning and other applications.

[0076] S1-1: Measure the relevant data of each standard section of the tower body in an undamaged state, including sensor detection values, geometric parameters and material characteristic parameters, such as the stress, vibration frequency and displacement of the tower body, the length, cross-sectional dimensions and elastic modulus of each standard section; use three-dimensional measurement technology, such as laser scanning or photogrammetry, to obtain the spatial position point coordinate information of each standard section of the tower body, and store the obtained information in the database; these coordinate data will be used to generate a three-dimensional model of the tower body.

[0077] S1-2: Import the collected data into 3D modeling software, such as AutoCAD, Revit, SolidWorks, etc., use the modeling tools of the software to generate a 3D model of the tower body according to the coordinates of the spatial position points, and add connectors and hole details to the 3D model to improve the accuracy of the 3D model;

[0078] Optionally, by conducting damage prevention inspection on the connections and holes;

[0079] S1-3: Extract the spatial position point coordinate set of the tower body according to the three-dimensional model of the tower body, denoted as P = {P i |i∈[1,n]}, where n represents the total number of spatial position coordinates of the tower, Pi Represents the coordinates of the i-th spatial position point, including the coordinate values ​​in the x, y, and z directions, P i =(x i ,y i , z i ), where x represents the direction from east to west, y represents the direction from south to north, and z represents the vertical direction;

[0080] Optionally, step S1-4 is also included: performing structural analysis on the established three-dimensional model using finite element analysis software, comparing the analysis results with data under actual working conditions, and verifying the reliability of the model.

[0081] S2: Monitor the real-time data of the tower crane and determine whether the tower crane is damaged through the central processing system;

[0082] S2-1: By installing sensors at the standard sections and connectors of the tower, the data collected by the sensors covers the tower, so as to comprehensively detect the status of the tower; monitor the real-time relevant data of the tower, including the stress, vibration frequency, displacement and other data of the tower;

[0083] S2-2: Establish a central processing system, which is used to store, process and analyze real-time data; transmit the real-time relevant data of the tower body monitored by the sensor to the central processing system, and the central processing system stores the received real-time relevant data and performs data preprocessing to form a first detection data set, which is recorded as F t ={C j |j∈[1,J]}, where F t represents the first detection data set at the tth time node, C j represents the real-time monitoring value uploaded by the jth sensor, and J represents the total number of sensors;

[0084] S2-3: Analyze the damage status of the tower body of the current tower crane through the central processing system, match the first detection data set with the first detection standard data set stored in the database, and determine whether the current tower body is damaged; the first detection standard data set is recorded as F f = {B j |j∈[1,J]},B j represents the corresponding detection value of the jth sensor in the non-destructive state; the matching degree D between the first detection data set and the first detection standard data set at the tth time node is calculated according to the following formula t :

[0085]

[0086] When D t = 0, it is determined that the tower body has no damage; when Dt When the standard difference value d preset in the database is exceeded, it is determined that the tower body at the tth time node is damaged; when D t does not exceed the standard difference value d preset in the database, and D t When the value is greater than 0, the tower body shall be inspected for damage prevention;

[0087] Exemplarily, the standard difference value preset in the database is selected according to the structure, height and material of the tower body standard section; when the height of the tower body increases, the standard difference value decreases;

[0088] Optionally, when the present invention is implemented, the first detection standard data set is selected according to site conditions, local climate and seasonal factors, and the first detection standard data set stored in the database is not unique.

[0089] S3: A damage prevention detection model is constructed based on the tower body related data in an undamaged state and the tower body related data at each time node obtained through monitoring. The real-time tower body related data is analyzed through the damage prevention detection model to predict the tower body damage risk;

[0090] S3-1: Based on the data set in the undamaged state, a damage prevention detection model is constructed, including the following steps:

[0091] S3-1-1: Combine the three-dimensional model of the tower body and mark the coordinates of the sensor position in the spatial position point coordinate set of the tower body to generate the spatial position point coordinate set of the sensor, denoted as Q = {Q j |j∈[1,J]}, where Q j represents the coordinates of the jth marked spatial position point, Q j =(x j ,y j , z j ); According to the coordinates of the sensor, select the reference point, assume that there is a dependency relationship between the sensors in the same plane in the z direction, and record the set of sensors with a dependency relationship as L = {L k |k∈[1,δ]}, where L k represents the kth group of sensor sets with dependent relationships, δ represents the number of sensor sets with dependent relationships, δ≤J;

[0092] S3-1-2: Calculate the risk value G(r) of the rth standard section of the tower body according to the following formula:

[0093]

[0094] Where r∈[1,R], R represents the number of standard sections of the tower; J r represents the total number of sensors on the rth standard section of the tower, δ rIt represents the total number of sensor sets with dependencies on the rth standard section of the tower body; ω1 and ω2 represent influence coefficients, which are preset by relevant personnel and selected according to the position of the tower body where the standard section is located. As the position of the tower body where the standard section is located increases, the influence coefficient ω1 increases and the influence coefficient ω2 decreases, ω1+ω2=1;

[0095] Optionally, the risk value is weighted based on the historical annotation data of the standard section;

[0096] S3-1-3: define the initial accumulator sum and initialize it to 0, import the formula G(r), when G(r) receives the input value, it returns an updated output value Y, define the independent variable sequence, including a series of independent variable values; input the data of each standard section in the second detection data set into the formula G(r), calculate G(r) to obtain the output value Y, and then update the accumulator sum, sum=sum+Y; when all the standard sections of the tower body are input, the last updated sum value is used as the detection value output by the model;

[0097] S3-1-4: Deploy the constructed loss prevention detection model to ensure the stability and reliability of the model in the actual environment; continuously monitor the performance of the model to ensure the accuracy and effectiveness of the model; optimize and update the model in a timely manner based on implementation data feedback;

[0098] S3-2: Based on the first detection data set in step S2, combined with the three-dimensional model of the tower body, a second detection data set is formed, wherein the second detection data set includes real-time relevant data of each standard section of the tower body;

[0099] S3-3: Input the second detection data set into the damage prevention detection model, and detect each standard section of the tower crane tower body through the damage prevention detection model. When the detection value output by the damage prevention detection model is less than R, it is determined that there is a damage risk to the current tower body; when the detection value output by the damage prevention detection model is greater than or equal to R, and the risk value of each standard section of the tower body is greater than or equal to 1, it is determined that there is no damage risk to the current tower body.

[0100] S4: Process the damage of the tower body according to the damage identification result of the current tower body in S2, locate the risk factors of the tower body according to the prediction result of the damage risk of the tower body in S3, and perform damage prevention treatment on the tower body according to the location of the risk factors of the tower body;

[0101] S4-1: Obtain the damage identification result of the current tower body in S2. When it is determined that the tower body is damaged, verify the type and degree of damage through non-destructive testing technology to determine the impact of the damage on the performance and construction safety of the tower crane. According to the type and degree of damage, formulate a corresponding maintenance plan, including repairing, replacing damaged parts, strengthening structural support and other measures; perform necessary maintenance and replacement of the tower body according to the maintenance plan; when the maintenance is completed, re-evaluate the health of the tower body, record the maintenance process and results, including the materials, methods, personnel used, etc., and generate a maintenance report as part of the tower crane maintenance record.

[0102] Exemplarily, the non-destructive testing technology may be ultrasonic testing, X-ray testing, magnetic particle testing, penetration testing, etc., through which cracks, corrosion, and other damages inside the tower body may be discovered.

[0103] S4-2: Obtain the prediction result of the tower damage risk in S3, and when it is determined that the current tower has a damage risk, locate the risk factors of the tower;

[0104] When G(r) < 1, it is determined that the rth standard section of the tower contains risk factors, and the rth standard section is marked for risk, and the specific spatial position of the standard section containing risk factors is located. When the tower crane is climbing, the operating parameters of the climbing mechanism within the rth standard section of the tower are adjusted to reduce the risk of damage.

[0105] S4-3: Issue a warning signal, report the specific spatial location information of the standard section containing risk elements, and provide feedback to relevant management personnel.

[0106] During the long-term use of the tower crane, the climbing mechanism's excessive speed or inaccurate position adjustment may cause impact and vibration to any standard section of the tower body. If the risk factors cannot be detected and maintained in time, the accumulation of time may cause structural fatigue and local damage to the tower body, ultimately affecting the safe use of the tower crane.

[0107] The risk factors are located according to the prediction results of the model, and the standard sections of the tower body with damage risks are marked. According to the usage characteristics of the tower crane, the climbing wear of the marked standard sections is reduced by adjusting the usage frequency or usage order of the marked standard sections, thereby avoiding damage to the standard sections of the tower body during the operation of the climbing mechanism and improving the safety performance of the tower crane.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0109] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A tower crane damage prevention intelligent detection method based on big data, characterized by: The method comprises the following steps: S1: Obtain the tower body related data of the tower crane in an undamaged state, and generate a three-dimensional model of the tower body through three-dimensional modeling software; S2: Monitor the real-time data of the tower crane and determine whether the tower crane is damaged through the central processing system; S3: A damage prevention detection model is constructed based on the tower body related data in an undamaged state and the tower body related data at each time node obtained through monitoring. The real-time tower body related data is analyzed through the damage prevention detection model to predict the tower body damage risk; S4: Process the damage of the tower body according to the damage identification result of the current tower body in S2, locate the risk factors of the tower body according to the prediction result of the damage risk of the tower body in S3, and perform damage prevention treatment on the tower body according to the location of the risk factors of the tower body; The S2 comprises the following steps: S2-1: Monitor the real-time relevant data of the tower by installing sensors on the tower; S2-2: Establish a central processing system, which is used to store, process and analyze real-time data; transmit the real-time relevant data of the tower body monitored by the sensor to the central processing system, and the central processing system stores the received real-time relevant data and performs data preprocessing to form a first detection data set, which is recorded as F t ={C j |j∈[1,J]}, where F t represents the first detection data set at the tth time node, C j represents the real-time monitoring value uploaded by the jth sensor, and J represents the total number of sensors; S2-3: Analyze the damage status of the tower body of the current tower crane through the central processing system, match the first detection data set with the first detection standard data set stored in the database, and determine whether the current tower body is damaged; the first detection standard data set is recorded as F f = {B j |j∈[1,J]},B j represents the corresponding detection value of the jth sensor in the non-destructive state; the matching degree D between the first detection data set and the first detection standard data set at the tth time node is calculated according to the following formula t : When D t = 0, it is determined that the tower body has no damage; when D t When the standard difference value d preset in the database is exceeded, it is determined that the tower body at the tth time node is damaged; when D t does not exceed the standard difference value d preset in the database, and D t >0, conduct damage prevention inspection on the tower body; The S3 comprises the following steps: S3-1: Based on the data set in the undamaged state, a damage prevention detection model is constructed, including the following steps: S3-1-1: Combine the three-dimensional model of the tower body and mark the coordinates of the sensor position in the spatial position point coordinate set of the tower body to generate the spatial position point coordinate set of the sensor, denoted as Q = {Q j |j∈[1,J]}, where Q j Indicates the coordinates of the jth marked spatial position point, including the coordinate values ​​of the three directions of x, y, and z, where the x direction represents the east-west direction, the y direction represents the north-south direction, and the z direction represents the vertical direction. j =(xj, yj, z j ); According to the coordinates of the sensor, select the reference point, assume that there is a dependency relationship between the sensors in the same plane in the z direction, and record the set of sensors with a dependency relationship as L = {L k |k∈[1,δ]}, where L k represents the kth group of sensor sets with dependent relationships, δ represents the number of sensor sets with dependent relationships, δ≤J; S3-1-2: Calculate the risk value G(r) of the rth standard section of the tower body according to the following formula: Where r∈[1,R], R represents the number of standard sections of the tower; J r represents the total number of sensors on the rth standard section of the tower, δ r represents the total number of sensor sets with dependencies on the rth standard section of the tower; ω1 and ω2 represent influence coefficients, which are preset by relevant personnel; S3-1-3: define the initial accumulator sum and initialize it to 0, import the formula G(r), input the data of each standard section in the second detection data set into the formula G(r), calculate G(r) to obtain the output value, and then update the accumulator sum; when all the standard sections of the tower body are input, the last updated sum value is used as the detection value output by the model; S3-2: Based on the first detection data set in step S2, combined with the three-dimensional model of the tower body, a second detection data set is formed, wherein the second detection data set includes real-time relevant data of each standard section of the tower body; S3-3: Input the second detection data set into the damage prevention detection model, and detect each standard section of the tower crane tower body through the damage prevention detection model. When the detection value output by the damage prevention detection model is less than R, it is determined that there is a damage risk to the current tower body; when the detection value output by the damage prevention detection model is greater than or equal to R, and the risk value of each standard section of the tower body is greater than or equal to 1, it is determined that there is no damage risk to the current tower body.

2. According to the big data-based tower crane damage prevention intelligent detection method of claim 1, it is characterized by: The S1 comprises the following steps: S1-1: Measure the relevant data of each standard section of the tower body in an undamaged state, including sensor detection values, geometric parameters and material characteristic parameters; use three-dimensional measurement technology to obtain the spatial position point coordinate information of each standard section of the tower body, and store the obtained information in the database; S1-2: Import the collected data into the 3D modeling software, and use the modeling tools of the software to generate a 3D model of the tower body according to the coordinates of the spatial position points; S1-3: Extract the spatial position point coordinate set of the tower body, denoted as P = {P i |i∈[1,n]}, where n represents the total number of spatial position coordinates of the tower, P i represents the coordinates of the i-th spatial position point, P i =(x i ,y i , z i ).

3. The tower crane damage prevention intelligent detection method based on big data according to claim 1 is characterized by: The S4 comprises the following steps: S4-1: Obtain the damage identification result of the current tower body in S2. When it is determined that the tower body is damaged, verify the type and degree of the damage through non-destructive testing technology, and formulate a corresponding maintenance plan according to the type and degree of the damage; perform necessary maintenance and replacement on the tower body according to the maintenance plan; S4-2: Obtain the prediction result of the tower damage risk in S2, and when it is determined that the current tower has a damage risk, locate the risk factors of the tower; When G(r) < 1, it is determined that the rth standard section of the tower contains risk factors, the rth standard section is marked for risk, the specific spatial position of the standard section containing risk factors is located, and when the tower crane is climbing, the operating parameters of the climbing mechanism within the rth standard section of the tower are adjusted; S4-3: Issue a warning signal, report the specific spatial location information of the standard section containing risk elements, and provide feedback to relevant management personnel.

4. A tower crane damage prevention intelligent detection system based on big data, which executes a tower crane damage prevention intelligent detection method based on big data as described in any one of claims 1 to 3, characterized in that: The system includes: tower crane data acquisition module, tower crane data monitoring module, loss prevention intelligent detection module and damage management module; The tower crane data acquisition module is used to collect tower crane tower body related data, and build a tower body three-dimensional model based on the collected data, and store the tower body related data in a non-destructive state in a database; The tower crane data monitoring module is used to monitor the real-time tower crane tower body related data, determine whether the tower body is damaged, and process the tower body related data collected at each time node; The damage prevention intelligent detection module is used to detect the tower body state through the damage prevention detection model, predict the damage risk of the tower body, and transmit the prediction result to the damage state management module; The damage management module is used to process the monitored tower body damage, locate the risk factors of the tower body, and perform damage prevention processing on the tower body according to the location of the risk factors of the tower body.

Images