Crane safety early warning method based on data driving and application thereof

Abstract

The invention discloses a crane safety early warning method based on data driving and application thereof.According to the scheme, a public area in a working site of a tower crane is monitored in real time, so that a dynamic object in the site can be monitored, and when a lifting appliance assembly of the subsequent crane transfers an object, the safety early warning of the crane is achieved. Data guarantee is provided for efficient and comprehensive field monitoring; according to the early warning mechanism, under the condition that the position information of the lifting appliance assembly, the carrier and the worker in the working site is monitored in real time, the prediction position of a certain time step length is established, certain position pre-judgment is provided for the lifting appliance assembly when the to-be-transferred object is transferred, and the accuracy of the to-be-transferred object is improved. And movement interference or other risk problems between the lifting appliance assembly or the transferred object and a carrier and a worker in a working site are avoided. According to the scheme, PID is further used for adjusting the speed change, so that the speed change is more stable when the moving speed of the lifting appliance assembly is adjusted; and the control stability of components of the crane is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crane control, and in particular to a data-driven crane safety early warning method and application thereof. Background Art

[0002] As an important transfer equipment, cranes are widely used in workshops, warehouses, ports, construction sites and other scenes. Tower cranes are typical outdoor crane equipment. Compared with indoor environments, the factors affecting their work are more complicated, such as environmental wind, temperature, humidity, rain, etc. These environmental factors often have characteristics such as variable and nonlinear changes. Therefore, when the crane is working outdoors, its safety monitoring and abnormal monitoring need to be more precise and strict. Since there may be many vehicles and workers moving in the work site of the tower crane, when the tower crane is working, it is necessary not only to monitor its own parameters, but also to closely track whether the safety distance between the tower crane's hoisting assembly and the vehicles and workers in the site is less than the preset value during the movement of the tower crane's hoisting assembly. However, most of the early warning schemes disclosed in the current literature mostly provide sound and light alarms to remind vehicles and workers. The disclosure of the crane's working parameters, such as the speed at which the hoisting assembly is driven to move and parameter intervention, is still relatively rare.

[0003] Therefore, how to monitor and optimize the safe distance of tower cranes working on site, and how to intervene in their work control when warning events occur, are research topics with positive and practical significance. Summary of the invention

[0004] In view of this, the purpose of the present invention is to propose a data-driven crane safety warning method and its application, which is reliable in implementation, flexible in application, quick in response, and capable of intervening in the working parameters of the crane based on the actual relative distance situation.

[0005] In order to achieve the above technical objectives, the technical solution adopted by the present invention is:

[0006] A data-driven crane safety early warning method for tower crane safety early warning, comprising:

[0007] S01. Conduct real-time monitoring of the public areas within the work site where the tower crane is located to generate on-site monitoring data;

[0008] S02, responding to the work start signal of the tower crane, determining the posture of the tower crane, and generating posture data;

[0009] S03, obtaining on-site monitoring data, determining the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and constructing a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane;

[0010] S04, obtaining a transfer work instruction, parsing to obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then planning a transfer path for the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generating work trajectory information;

[0011] S05. The tower crane starts working according to the working trajectory information, and at the same time, performs real-time monitoring on dynamic objects in the working site to generate dynamic object trajectory information;

[0012] S06. Obtaining the trajectory information of the dynamic object, combining it with the working trajectory information of the tower crane, determining whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generating a warning determination result;

[0013] S07. Obtain a warning judgment result, and when it indicates that the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, generate a warning signal and / or intervene in the action of the tower crane.

[0014] As a possible implementation, further, the solution S01 also includes:

[0015] Collect data on the terrain, fixed buildings and fixed equipment in the work site where the tower crane is located by manual entry and / or equipment scanning to obtain site obstacle data;

[0016] Wherein, a plurality of image acquisition modules, laser radar modules and / or ultrasonic sensor modules are deployed in the work site; the on-site monitoring data includes image monitoring data, laser radar monitoring data and / or ultrasonic monitoring data correspondingly generated by the image acquisition modules, laser radar modules and / or ultrasonic sensor modules;

[0017] The dynamic object is a vehicle or a staff member, which carries a positioning module for feeding back its real-time position in the workplace. Each positioning module has a unique ID number and object information. The object information is the vehicle type or personnel identity information. The positioning module is used to feed back the position information of the dynamic object in real time and generate positioning data corresponding to the dynamic object one by one.

[0018] As a better implementation option, preferably, positioning modules are deployed on the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley of the tower crane described in this scheme, and each positioning module has a unique ID number, and the position information of the positioning module on the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley is recorded.

[0019] As a preferred implementation option, preferably, in the present scheme S02, the positioning data of the positioning modules on the tower crane's balance arm, lifting arm, sling assembly, tower body and load-carrying trolley are fed back to determine the position points of the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley in the work site, and then the position points are virtually connected according to preset conditions based on the ID number of the positioning module to generate a brief outline, and then the preset outlines of the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley and the position of the positioning module thereon are combined to perform inversion to determine the posture of the tower crane and generate posture data.

[0020] As a preferred implementation option, preferably, this solution S03 includes:

[0021] S031, acquiring on-site monitoring data, and extracting multiple image monitoring data acquired by multiple image acquisition modules;

[0022] S032, extracting frames from a plurality of image monitoring data at intervals to obtain images at a plurality of different time points;

[0023] S033, positioning the elements in the image respectively, marking them as suspected dynamic objects according to the position changes of the elements in the image at different time points in the same image monitoring data, and identifying the elements marked as suspected dynamic objects to determine whether they are staff or vehicles;

[0024] S034. Acquire positioning data generated by a positioning module carried by the dynamic object, and use the site obstacle data corresponding to the workplace as a reference to further judge the elements marked as suspected dynamic objects in the image, so as to determine the dynamic objects in the workplace and uniquely identify them;

[0025] S034, tracking the dynamic object in real time in the image monitoring data collected and generated by the multiple image acquisition modules to generate dynamic object movement information;

[0026] S035. The posture data of the tower crane is used to determine the position information of the lifting equipment components thereon, and combined with the dynamic object movement information, a dynamic model of the work site where the tower crane is located is constructed.

[0027] As a preferred implementation option, preferably, this solution S035 includes:

[0028] S0351. Acquire the posture data of the tower crane, and determine the position information C of the spreader assembly according to the positioning data fed back by the positioning module corresponding to the spreader assembly and the position information of the positioning module on the spreader assembly. t (x c ,y c , z c ), t is the timestamp when the location information is determined;

[0029] S0352, obtain the movement information of the dynamic object, combine it with the positioning data fed back by the corresponding positioning module, and define the position information of the staff as P n，t (x p ,y p , z p ), the position information of the vehicle is defined as V n，t (x v ,y v , z v );t is the timestamp when the location information is determined, and n is the ID number of the staff member or vehicle;

[0030] The position information of all dynamic objects and crane spreader components are mapped to a unified three-dimensional space coordinate system, namely the global coordinate system, which is defined as follows:

[0031] P global =P local ·T sensor

[0032] Among them, P global is the position information of the target object in the global coordinate system, wherein the target object is a dynamic object and / or a crane spreader assembly; T sensor is the transformation matrix from the target object to the global coordinate system, P local The position information of the target object obtained based on the sensor;

[0033] S0353. Based on the changes in the position information of the crane sling components, carriers, and workers in the workplace over time, a dynamic model E(t) of the workplace where the tower crane is located is constructed, which is defined as:

[0034] E(t)={C(t), V n (t), P n (t)},

[0035] Among them, C(t) is the motion state set of the spreader assembly, which is defined as:

[0036] C(t)=(x c (t), y c (t), z c (t), v c(t), a c (t))

[0037] x c (t), y c (t), z c (t), v c (t), a c (t) are the x, y, z coordinate data, velocity, and acceleration of the spreader assembly at time t;

[0038] V n (t) is the vehicle motion state set, n is the vehicle ID number, which is defined as:

[0039] V n (t) = (x v (t), y v (t), z v (t), v v (t), a v (t))

[0040] x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the vehicle at time t;

[0041] P n (t) is the vehicle motion state set, n is the ID number of the worker, which is defined as:

[0042] P n (t) = (x p (t), y p (t), z p (t), v p (t), a p (t))

[0043] x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the worker at time t.

[0044] As a preferred implementation option, preferably, this solution S04 includes:

[0045] S041. Obtain the transfer work instruction, parse and obtain the current location of the object to be transferred, set it as the first target location, and the destination to which the object to be transferred needs to be transferred, set it as the second target location;

[0046] S042, planning a first path of the tower crane's spreader assembly from its current position to a first target position and a second path from the first target position to a second target position according to the state information of the tower crane and the position information of the spreader assembly, combined with the site obstacle data, and then generating work trajectory information;

[0047] When planning the transfer route, an optimal path function is established, which is defined as follows:

[0048]

[0049] Among them, f(x c ,y c , z c , t) is the path cost function, which includes obstacle avoidance and energy consumption;

[0050] Path planning uses a heuristic search based on the A* algorithm, with the goal of finding the path with the minimum cost function:

[0051] The cost function is defined as follows:

[0052] f(x c ,y c , z c , t) = g(x c ,y c , z c )+h(x c ,y c , z c )

[0053] Among them, g(x c ,y c , z c ) is the actual cost of the current position of the spreader component as the starting point, that is, the cumulative path length; h(x c ,y c , z c ) is the heuristic estimate of the spreader component to the target point, i.e., the Euclidean distance;

[0054] Establish obstacle avoidance constraints so that path planning meets the following definitions:

[0055] d min (t) = min(||C t -V n，t ||,||C t -P n，t ||)>d safe

[0056] Right now,

[0057] dmin (t) = min(||(x c ,y c , z c )-(x v ,y v , z v )||,||(x c ,y c , z c )-(x p ,y p , z p )||)>d safe

[0058] Among them, d min (t) is the minimum distance between the sling assembly and the carrier and workers in the workplace, d safe The preset safety distance.

[0059] As a preferred implementation option, preferably, this solution S05 includes:

[0060] S051, the tower crane starts working according to the working trajectory information, and at the same time, monitors the dynamic objects in the working site in real time, and then updates the dynamic model E(t) in real time;

[0061] S052. Based on the dynamic model E(t), the movement trajectory of the spreader assembly, the carrier, and the staff in the past preset time period is obtained. On this basis, the historical trajectory function x(t) is formulated, and then the position information of the spreader assembly, and the carrier and staff within the preset range in the future time interval Δt is predicted by combining the kinematic formula and Kalman filtering to obtain the predicted position, which is defined as follows:

[0062]

[0063] Where x(t+Δt) is the predicted position of the spreader assembly, carrier or worker at time t+Δt; v(t) is the velocity at time t, a(t) is the acceleration at time t, and Δt is the prediction time step;

[0064] The predicted position is combined with the real-time updated dynamic model E(t) to generate dynamic object trajectory information.

[0065] As a preferred implementation option, preferably, this solution S06 includes:

[0066] The trajectory information of the dynamic object is obtained, and combined with the working trajectory information of the tower crane, it is determined whether the safe distance between the spreader component and the dynamic object during the movement is less than the preset warning threshold, and a warning judgment result is generated.

[0067] As a preferred implementation option, preferably, in the present solution S07, intervening in the action of the tower crane includes:

[0068] The speed at which the spreader assembly is driven to move is dynamically adjusted according to the relative minimum distance between the spreader assembly of the tower crane and the carrier or the staff. The control formula is:

[0069]

[0070] Among them, v c (t) is the speed of the spreader assembly at time t; v max is the maximum speed of the spreader assembly when driven, d(t) is the relative minimum distance between the spreader assembly and the carrier or the worker, Δd is the preset buffer distance, d safe Preset safe distance between spreader components and carriers or workers;

[0071] The speed is adjusted by PID control to ensure smooth speed changes, which is defined as follows:

[0072]

[0073] Where, e(t) = d(t) - d safe , K p , K i , K d They are the proportional, integral and differential gain coefficients of PID control respectively.

[0074] Based on the above, the present solution also proposes a tower crane operation risk avoidance method, which includes the above-mentioned data-driven crane safety warning method.

[0075] Based on the above, this scheme also proposes a data-driven crane safety warning system, which includes:

[0076] The on-site monitoring module is used to monitor the public areas in the work site where the tower crane is located in real time and generate on-site monitoring data;

[0077] A crane monitoring module is used to respond to a work start signal of the tower crane, determine the posture of the tower crane, and generate posture data;

[0078] The data fusion module is used to obtain the on-site monitoring data, determine the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and build a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane;

[0079] The route planning module is used to obtain the transfer work instruction, parse and obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then plan the transfer path of the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generate work trajectory information;

[0080] A dynamic object tracking module is used to respond to the signal of the tower crane starting work according to the work trajectory information, monitor the dynamic objects in the work site in real time, and generate dynamic object trajectory information;

[0081] A data judgment module is used to obtain the trajectory information of the dynamic object, and combine the working trajectory information of the tower crane to judge whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generate a warning judgment result;

[0082] The early warning intervention module is used to obtain the early warning judgment result, and when it points to the safety distance between the spreader assembly and the dynamic object is less than a preset early warning threshold, it generates an early warning signal and / or intervenes in the action of the tower crane.

[0083] By adopting the above-mentioned technical scheme, the present invention has the following beneficial effects compared with the prior art: the present scheme performs real-time monitoring of the public area in the working site of the tower crane, so that dynamic objects in the site can be monitored, and by matching the on-site monitoring data obtained at different time points, it is possible to quickly and conveniently determine which objects are dynamic objects (such as vehicles, staff) and which are static objects (such as terrain, buildings, etc.) within the monitoring range; and provide data guarantee for efficient and comprehensive on-site monitoring of the subsequent crane's sling components when transporting objects. In addition, this solution cleverly deploys the positioning module on the crane's balance arm, lifting arm, spreader assembly, tower body and load trolley, so that after the positioning module feeds back the positioning data, it can quickly determine the spatial position of the tower crane components in the site according to the deployment position of the positioning module on the crane components, and the virtual connection between different positioning modules can provide a reliable and efficient reference for the inversion of the tower crane's posture profile; in terms of the early warning mechanism, this solution establishes a certain time step prediction position for the spreader assembly when transporting the objects to be transported by real-time monitoring of the position information of the spreader assembly, carrier, and staff in the workplace, so as to provide a certain position prediction for the spreader assembly when transporting the objects to be transported, and avoid the spreader assembly or the transported objects and the carrier and staff in the workplace. There are other risk problems. When the relative distance between the spreader assembly and the dynamic objects in the field changes, this solution provides more reliable and flexible working speed control for the crane when transporting objects by setting different spreader movement speed limits, and further uses PID to adjust the speed change, so that the spreader assembly has a smoother speed change when the movement speed is adjusted; the control stability of the crane components is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0085] Figure 1 This is a brief implementation flow diagram of the safety early warning method of this scheme;

[0086] Figure 2 This is a brief connection diagram of the unit modules of the safety warning system of this scheme. DETAILED DESCRIPTION

[0087] The present invention will be further described in detail below in conjunction with the accompanying drawings and examples. It is particularly noted that the following examples are only used to illustrate the present invention, but are not intended to limit the scope of the present invention. Similarly, the following examples are only partial embodiments of the present invention rather than all embodiments, and all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0088] like Figure 1 As shown, the scheme is a data-driven crane safety early warning method for tower crane safety early warning, which includes:

[0089] S01. Conduct real-time monitoring of the public areas within the work site where the tower crane is located to generate on-site monitoring data;

[0090] S02, responding to the work start signal of the tower crane, determining the posture of the tower crane, and generating posture data;

[0091] S03, obtaining on-site monitoring data, determining the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and constructing a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane;

[0092] S04, obtaining a transfer work instruction, parsing to obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then planning a transfer path for the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generating work trajectory information;

[0093] S05. The tower crane starts working according to the working trajectory information, and at the same time, performs real-time monitoring on dynamic objects in the working site to generate dynamic object trajectory information;

[0094] S06. Obtaining the trajectory information of the dynamic object, combining it with the working trajectory information of the tower crane, determining whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generating a warning determination result;

[0095] S07. Obtain a warning judgment result, and when it indicates that the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, generate a warning signal and / or intervene in the action of the tower crane.

[0096] This solution enables real-time monitoring of public areas within the tower crane's work site, so that dynamic objects within the site can be monitored. By matching the on-site monitoring data obtained at different time points, it can quickly and conveniently determine which objects within the monitoring range are dynamic objects (such as vehicles, workers) and which are static objects (such as terrain, buildings, etc.); providing data support for efficient and comprehensive on-site monitoring of subsequent crane sling components when transporting objects.

[0097] In order to improve the precision of monitoring in the workplace, as a possible implementation method, further, this solution S01 also includes:

[0098] Data on the terrain, fixed buildings and fixed equipment in the work site where the tower crane is located is collected by manual entry and / or equipment scanning to obtain site obstacle data.

[0099] In terms of obtaining the location data, a plurality of image acquisition modules, laser radar modules and / or ultrasonic sensor modules are deployed in the work site; the on-site monitoring data includes image monitoring data, laser radar monitoring data and / or ultrasonic monitoring data correspondingly generated by the image acquisition modules, laser radar modules and / or ultrasonic sensor modules;

[0100] The dynamic object is a vehicle or a staff member, which carries a positioning module for feeding back its real-time position in the workplace. Each positioning module has a unique ID number and object information. The object information is the vehicle type or personnel identity information. The positioning module is used to feed back the position information of the dynamic object in real time and generate positioning data corresponding to the dynamic object one by one.

[0101] In order to more conveniently determine the posture of the crane, as a better implementation option, preferably, the tower crane described in this scheme is equipped with positioning modules on the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley, and each positioning module has a unique ID number, and the position information of the positioning module on the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley is recorded.

[0102] As a preferred implementation option, preferably, in the present scheme S02, the positioning data of the positioning modules on the tower crane's balance arm, lifting arm, sling assembly, tower body and load-carrying trolley are fed back to determine the position points of the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley in the work site, and then the position points are virtually connected according to preset conditions based on the ID number of the positioning module to generate a brief outline, and then the preset outlines of the balance arm, lifting arm, sling assembly, tower body and load-carrying trolley and the position of the positioning module thereon are combined to perform inversion to determine the posture of the tower crane and generate posture data.

[0103] This solution cleverly deploys positioning modules on the crane's balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley. After the positioning module feeds back the positioning data, it can quickly determine the spatial position of the tower crane components in the site based on the deployment position of the positioning module on the crane components. The virtual connections between different positioning modules can provide a reliable and efficient reference for the inversion of the tower crane's posture contour.

[0104] In data fusion processing, as a better implementation option, preferably, this solution S03 includes:

[0105] S031, acquiring on-site monitoring data, and extracting multiple image monitoring data acquired by multiple image acquisition modules;

[0106] S032, extracting frames from a plurality of image monitoring data at intervals to obtain images at a plurality of different time points;

[0107] S033, positioning the elements in the image respectively, marking them as suspected dynamic objects according to the position changes of the elements in the image at different time points in the same image monitoring data, and identifying the elements marked as suspected dynamic objects to determine whether they are staff or vehicles;

[0108] S034. Acquire positioning data generated by a positioning module carried by the dynamic object, and use the site obstacle data corresponding to the workplace as a reference to further judge the elements marked as suspected dynamic objects in the image, so as to determine the dynamic objects in the workplace and uniquely identify them;

[0109] S034, tracking the dynamic object in real time in the image monitoring data collected and generated by the multiple image acquisition modules to generate dynamic object movement information;

[0110] S035. The posture data of the tower crane is used to determine the position information of the lifting equipment components thereon, and combined with the dynamic object movement information, a dynamic model of the work site where the tower crane is located is constructed.

[0111] Based on the above, as a better implementation option, preferably, this solution S035 includes:

[0112] S0351. Acquire the posture data of the tower crane, and determine the position information C of the spreader assembly according to the positioning data fed back by the positioning module corresponding to the spreader assembly and the position information of the positioning module on the spreader assembly. t (x c ,y c , z c ), t is the timestamp when the location information is determined;

[0113] S0352, obtain the movement information of the dynamic object, combine it with the positioning data fed back by the corresponding positioning module, and define the position information of the staff as P n，t (x p ,y p , z p ), the position information of the vehicle is defined as V n，t (x v ,y v , z v );t is the timestamp when the location information is determined, and n is the ID number of the staff member or vehicle;

[0114] The position information of all dynamic objects and crane spreader components are mapped to a unified three-dimensional space coordinate system, namely the global coordinate system, which is defined as follows:

[0115] P global =P local ·T sensor

[0116] Among them, P global is the position information of the target object in the global coordinate system, wherein the target object is a dynamic object and / or a crane spreader assembly; T sensor is the transformation matrix from the target object to the global coordinate system, P local The position information of the target object obtained based on the sensor;

[0117] S0353. Based on the changes in the position information of the crane sling components, carriers, and workers in the workplace over time, a dynamic model E(t) of the workplace where the tower crane is located is constructed, which is defined as:

[0118] E(t)={C(t), V n (t), P n (t)},

[0119] Among them, C(t) is the motion state set of the spreader assembly, which is defined as:

[0120] C(t)=(xc (t), y c (t), z c (t), v c (t), a c (t))

[0121] x c (t), y c (t), z c (t), v c (t), a c (t) are the x, y, z coordinate data, velocity, and acceleration of the spreader assembly at time t;

[0122] V n (t) is the vehicle motion state set, n is the vehicle ID number, which is defined as:

[0123] V n (t) = (x v (t), y v (t), z v (t), v v (t), a v (t))

[0124] x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the vehicle at time t;

[0125] P n (t) is the vehicle motion state set, n is the ID number of the worker, which is defined as:

[0126] P n (t) = (x p (t), y p (t), z p (t), v p (t), a p (t))

[0127] x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the worker at time t.

[0128] In the trajectory planning of the crane spreader assembly moving in the field, as a better implementation option, preferably, this solution S04 includes:

[0129] S041. Obtain the transfer work instruction, parse and obtain the current location of the object to be transferred, set it as the first target location, and the destination to which the object to be transferred needs to be transferred, set it as the second target location;

[0130] S042, planning a first path of the tower crane's spreader assembly from its current position to a first target position and a second path from the first target position to a second target position according to the state information of the tower crane and the position information of the spreader assembly, combined with the site obstacle data, and then generating work trajectory information;

[0131] When planning the transfer route, an optimal path function is established, which is defined as follows:

[0132]

[0133] Among them, f(x c ,y c , z c , t) is the path cost function, which includes obstacle avoidance and energy consumption;

[0134] Path planning uses a heuristic search based on the A* algorithm, with the goal of finding the path with the minimum cost function:

[0135] The cost function is defined as follows:

[0136] f(x c ,y c , z c , t) = g(x c ,y c , z c )+h(x c ,y c , z c )

[0137] Among them, g(x c ,y c , z c ) is the actual cost of the current position of the spreader component as the starting point, that is, the cumulative path length; h(x c ,y c , z c ) is the heuristic estimate of the spreader component to the target point, i.e., the Euclidean distance;

[0138] Establish obstacle avoidance constraints so that path planning meets the following definitions:

[0139] d min (t) = min(||C t -V n，t ||,||C t -Pn，t ||)>d safe

[0140] Right now,

[0141] d min (t) = min(||(x c ,y c , z c )-(x v ,y v , z v )||,||(x c ,y c , z c )-(x p ,y p , z p )||)>d safe

[0142] Among them, d min (t) is the minimum distance between the sling assembly and the carrier and workers in the workplace, d safe The preset safety distance.

[0143] This scheme provides a more reliable and safe mechanism guarantee for the tower crane's spreader assembly when it is empty or lifting objects to be transported by establishing path planning constraints.

[0144] When the spreader assembly of the tower crane is moved, in order to improve its working safety, as a better implementation option, preferably, this solution S05 includes:

[0145] S051, the tower crane starts working according to the working trajectory information, and at the same time, monitors the dynamic objects in the working site in real time, and then updates the dynamic model E(t) in real time;

[0146] S052. Based on the dynamic model E(t), the movement trajectory of the spreader assembly, the carrier, and the staff in the past preset time period is obtained. On this basis, the historical trajectory function x(t) is formulated, and then the position information of the spreader assembly, and the carrier and staff within the preset range in the future time interval Δt is predicted by combining the kinematic formula and Kalman filtering to obtain the predicted position, which is defined as follows:

[0147]

[0148] Where x(t+Δt) is the predicted position of the spreader assembly, carrier or worker at time t+Δt; v(t) is the velocity at time t, a(t) is the acceleration at time t, and Δt is the prediction time step;

[0149] The predicted position is combined with the real-time updated dynamic model E(t) to generate dynamic object trajectory information.

[0150] This solution establishes a predicted position for a certain time step by real-time monitoring of the position information of the sling components, carriers, and workers in the workplace. This provides a certain position prediction for the sling components when they are transporting objects to be transported, thereby avoiding movement interference or other risky issues between the sling components or the transported objects and the vehicles and workers in the workplace.

[0151] As a preferred implementation option, preferably, this solution S06 includes:

[0152] The trajectory information of the dynamic object is obtained, and combined with the working trajectory information of the tower crane, it is determined whether the safe distance between the spreader component and the dynamic object during the movement is less than the preset warning threshold, and a warning judgment result is generated.

[0153] In terms of specific intervention measures, as a preferred implementation option, preferably, in this solution S07, intervention on the action of the tower crane includes:

[0154] The speed at which the spreader assembly is driven to move is dynamically adjusted according to the relative minimum distance between the spreader assembly of the tower crane and the carrier or the staff. The control formula is:

[0155]

[0156] Among them, v c (t) is the speed of the spreader assembly at time t; v max is the maximum speed of the spreader assembly when driven, d(t) is the relative minimum distance between the spreader assembly and the carrier or the worker, Δd is the preset buffer distance, d safe Preset safe distance between spreader components and carriers or workers;

[0157] The speed is adjusted by PID control to ensure smooth speed changes, which is defined as follows:

[0158]

[0159] Where, e(t) = d(t) - d safe , K p , K i , K d They are the proportional, integral and differential gain coefficients of PID control respectively.

[0160] This solution can provide more reliable and flexible working speed control when the crane transfers items by setting different spreader movement speed limits, and further uses PID to adjust the speed change, so that the speed change of the spreader component is smoother when the movement speed is adjusted, thereby improving the control stability of the crane components.

[0161] Based on the above, the present solution also proposes a tower crane operation risk avoidance method, which includes the above-mentioned data-driven crane safety warning method.

[0162] Combination Figure 2 As shown, based on the above, this scheme also proposes a data-driven crane safety warning system, which includes:

[0163] The on-site monitoring module is used to monitor the public areas in the work site where the tower crane is located in real time and generate on-site monitoring data;

[0164] A crane monitoring module is used to respond to a work start signal of the tower crane, determine the posture of the tower crane, and generate posture data;

[0165] The data fusion module is used to obtain the on-site monitoring data, determine the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and build a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane;

[0166] The route planning module is used to obtain the transfer work instruction, parse and obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then plan the transfer path of the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generate work trajectory information;

[0167] A dynamic object tracking module is used to respond to the signal of the tower crane starting work according to the work trajectory information, monitor the dynamic objects in the work site in real time, and generate dynamic object trajectory information;

[0168] A data judgment module is used to obtain the trajectory information of the dynamic object, and combine the working trajectory information of the tower crane to judge whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generate a warning judgment result;

[0169] The early warning intervention module is used to obtain the early warning judgment result, and when it points to the safety distance between the spreader assembly and the dynamic object is less than a preset early warning threshold, it generates an early warning signal and / or intervenes in the action of the tower crane.

[0170] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0172] The above descriptions are only some embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Any equivalent device or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A data-driven crane safety early warning method for tower crane safety early warning, characterized in that: It includes: S01. Conduct real-time monitoring of the public areas within the work site where the tower crane is located to generate on-site monitoring data; S02, responding to the work start signal of the tower crane, determining the posture of the tower crane, and generating posture data; S03, obtaining on-site monitoring data, determining the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and constructing a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane; S04, obtaining a transfer work instruction, parsing to obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then planning a transfer path for the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generating work trajectory information; S05. The tower crane starts working according to the working trajectory information, and at the same time, performs real-time monitoring on dynamic objects in the working site to generate dynamic object trajectory information; S06. Obtaining the trajectory information of the dynamic object, combining it with the working trajectory information of the tower crane, determining whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generating a warning determination result; S07. Obtain a warning judgment result, and when it indicates that the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, generate a warning signal and / or intervene in the action of the tower crane.

2. The data-driven crane safety early warning method according to claim 1, characterized in that: S01 also includes: Collect data on the terrain, fixed buildings and fixed equipment in the work site where the tower crane is located by manual entry and / or equipment scanning to obtain site obstacle data; Wherein, a plurality of image acquisition modules, laser radar modules and / or ultrasonic sensor modules are deployed in the work site; the on-site monitoring data includes image monitoring data, laser radar monitoring data and / or ultrasonic monitoring data correspondingly generated by the image acquisition modules, laser radar modules and / or ultrasonic sensor modules; The dynamic object is a vehicle or a staff member, which carries a positioning module for feeding back its real-time position in the workplace. Each positioning module has a unique ID number and object information. The object information is the vehicle type or personnel identity information. The positioning module is used to feed back the position information of the dynamic object in real time and generate positioning data corresponding to the dynamic object one by one.

3. The data-driven crane safety early warning method according to claim 2, characterized in that: Positioning modules are deployed on the balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley of the tower crane, and each positioning module has a unique ID number, and the position information of the positioning module on the balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley is recorded; In S02, the positioning data of the positioning modules on the tower crane's balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley are fed back to determine the position points of the balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley in the work site, and then the position points are virtually connected according to preset conditions based on the ID number of the positioning module to generate a brief outline. Then, combined with the preset outlines of the balance arm, lifting arm, spreader assembly, tower body and load-carrying trolley and the position of the positioning module thereon, the posture of the tower crane is determined by inversion to generate posture data.

4. The data-driven crane safety early warning method according to claim 3, characterized in that: S03 includes: S031, acquiring on-site monitoring data, and extracting multiple image monitoring data acquired by multiple image acquisition modules; S032, extracting frames from a plurality of image monitoring data at intervals to obtain images at a plurality of different time points; S033, positioning the elements in the image respectively, marking them as suspected dynamic objects according to the position changes of the elements in the image at different time points in the same image monitoring data, and identifying the elements marked as suspected dynamic objects to determine whether they are staff or vehicles; S034. Acquire positioning data generated by a positioning module carried by the dynamic object, and use the site obstacle data corresponding to the workplace as a reference to further judge the elements marked as suspected dynamic objects in the image, so as to determine the dynamic objects in the workplace and uniquely identify them; S034, tracking the dynamic object in real time in the image monitoring data collected and generated by the multiple image acquisition modules to generate dynamic object movement information; S035. The posture data of the tower crane is used to determine the position information of the lifting equipment components thereon, and combined with the dynamic object movement information, a dynamic model of the work site where the tower crane is located is constructed.

5. The data-driven crane safety early warning method according to claim 4, characterized in that: S035 includes: S0351. Acquire the posture data of the tower crane, and determine the position information C of the spreader assembly according to the positioning data fed back by the positioning module corresponding to the spreader assembly and the position information of the positioning module on the spreader assembly. t (x c ,y c , z c ), t is the timestamp when the location information is determined; S0352, obtain the movement information of the dynamic object, combine it with the positioning data fed back by the corresponding positioning module, and define the position information of the staff as P n，t (x p ,y p , z p ), the position information of the vehicle is defined as V n，t (x v ,y v , z v );t is the timestamp when the location information is determined, and n is the ID number of the staff member or vehicle; The position information of all dynamic objects and crane spreader components are mapped to a unified three-dimensional space coordinate system, namely the global coordinate system, which is defined as follows: P global =P local ·T sensor Among them, P global is the position information of the target object in the global coordinate system, wherein the target object is a dynamic object and / or a crane spreader assembly; T sensor is the transformation matrix from the target object to the global coordinate system, P local The position information of the target object obtained based on the sensor; S0353. Based on the changes in the position information of the crane sling components, carriers, and workers in the workplace over time, a dynamic model E(t) of the workplace where the tower crane is located is constructed, which is defined as: E(t)={C(t),V n (t),P n (t)}, Among them, C(t) is the motion state set of the spreader assembly, which is defined as: C(t)=(x c (t),y c (t),z c (t),v c (t),a c (t)) x c (t), y c (t), z c (t), v c (t), a c (t) are the x, y, z coordinate data, velocity, and acceleration of the spreader assembly at time t; V n (t) is the vehicle motion state set, n is the vehicle ID number, which is defined as: V n (t)=(x v (t),y v (t),a v (t),v v (t),a v (t)) x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the vehicle at time t; P n (t) is the vehicle motion state set, n is the ID number of the worker, which is defined as: P n (t)=(x p (t),y p )t),z p (t),v p (t),a p (t)) x v (t), y v (t), z v (t), v v (t), a v (t) are the x, y, z coordinate data, velocity, and acceleration of the worker at time t.

6. The data-driven crane safety early warning method according to claim 5, characterized in that: S04 includes: S041. Obtain the transfer work instruction, parse and obtain the current location of the object to be transferred, set it as the first target location, and the destination to which the object to be transferred needs to be transferred, set it as the second target location; S042, planning a first path of the tower crane's spreader assembly from its current position to a first target position and a second path from the first target position to a second target position according to the state information of the tower crane and the position information of the spreader assembly, combined with the site obstacle data, and then generating work trajectory information; When planning the transfer route, an optimal path function is established, which is defined as follows: Minmize: Among them, f(x c ,y c , z c , t) is the path cost function, which includes obstacle avoidance and energy consumption; Path planning uses a heuristic search based on the A* algorithm, with the goal of finding the path with the minimum cost function: The cost function is defined as follows: f(x c ,y c ,z c ,t)=g(x c ,y c ,z c )+h(x c ,y c ,z c ) Among them, g(x c ,y c , z c ) is the actual cost of the current position of the spreader component as the starting point, that is, the cumulative path length; h(x c ,y c , z c ) is the heuristic estimate of the spreader component to the target point, i.e., the Euclidean distance; Establish obstacle avoidance constraints so that path planning meets the following definitions: d min (t)=min(||C t -V n，t ||,||C t -P n，t ||)>d safe Right now, d min (t)=min(||(x c ,y c ,z c )-(x v ,y v ,z v )||,||(x c ,y c ,z c )-(x p ,y p ,z p )||)>d safe Among them, d min (t) is the minimum distance between the sling assembly and the carrier and workers in the workplace, d safe The preset safety distance.

7. The data-driven crane safety early warning method according to claim 6, characterized in that: S05 includes: S051, the tower crane starts working according to the working trajectory information, and at the same time, monitors the dynamic objects in the working site in real time, and then updates the dynamic model E(t) in real time; S052. Based on the dynamic model E(t), the movement trajectory of the spreader assembly, the carrier, and the staff in the past preset time period is obtained. On this basis, the historical trajectory function x(t) is formulated, and then the position information of the spreader assembly, and the carrier and staff within the preset range in the future time interval Δt is predicted by combining the kinematic formula and Kalman filtering to obtain the predicted position, which is defined as follows: Where x(t+Δt) is the predicted position of the spreader assembly, carrier or worker at time t+Δt; v(t) is the velocity at time t, a(t) is the acceleration at time t, and Δt is the prediction time step; The predicted position is combined with the real-time updated dynamic model E(t) to generate dynamic object trajectory information; S06 includes: The trajectory information of the dynamic object is obtained, and combined with the working trajectory information of the tower crane, it is determined whether the safe distance between the spreader component and the dynamic object during the movement is less than the preset warning threshold, and a warning judgment result is generated.

8. The data-driven crane safety early warning method according to claim 6, characterized in that: In S07, intervention in the tower crane's movements includes: The speed at which the spreader assembly is driven to move is dynamically adjusted according to the relative minimum distance between the spreader assembly of the tower crane and the carrier or the staff. The control formula is: Among them, v c (t) is the speed of the spreader assembly at time t; v max is the maximum speed of the spreader assembly when driven, d(t) is the relative minimum distance between the spreader assembly and the carrier or the worker, Δd is the preset buffer distance, d safe Preset safe distance between spreader components and carriers or workers; The speed is adjusted by PID control to ensure smooth speed changes, which is defined as follows: Where, e(t) = d(t) - d safe , K p , K i , K d They are the proportional, integral and differential gain coefficients of PID control respectively.

9. A tower crane working risk avoidance method, characterized in that: It includes the data-driven crane safety early warning method as described in one of claims 1 to 5.

10. A data-driven crane safety warning system, characterized in that: It includes: The on-site monitoring module is used to monitor the public areas in the work site where the tower crane is located in real time and generate on-site monitoring data; A crane monitoring module is used to respond to a work start signal of the tower crane, determine the posture of the tower crane, and generate posture data; The data fusion module is used to obtain the on-site monitoring data, determine the dynamic objects in the work site where the tower crane is located, and their corresponding movement information, and build a dynamic model of the work site where the tower crane is located in combination with the posture data of the tower crane; The route planning module is used to obtain the transfer work instruction, parse and obtain the first target location of the object to be transferred and the second target location to which it needs to be transferred, and then plan the transfer path of the tower crane's spreader assembly from its current location to the first target location and the second target location in sequence, and generate work trajectory information; A dynamic object tracking module is used to respond to the signal of the tower crane starting work according to the work trajectory information, monitor the dynamic objects in the work site in real time, and generate dynamic object trajectory information; A data judgment module is used to obtain the trajectory information of the dynamic object, and combine the working trajectory information of the tower crane to judge whether the safety distance between the spreader assembly and the dynamic object is less than a preset warning threshold, and generate a warning judgment result; The early warning intervention module is used to obtain the early warning judgment result, and when it points to the safety distance between the spreader assembly and the dynamic object is less than a preset early warning threshold, it generates an early warning signal and / or intervenes in the action of the tower crane.

Images