Self-adaptive anti-swing obstacle avoidance feedback control method and system for tower crane based on neural network

Abstract

The invention discloses a tower crane self-adaptive anti-swing obstacle avoidance feedback control method and system based on a neural network, and relates to electromechanical system technology control, the method comprises the following steps: using a Lagrangian method to establish a kinetic model of a four-degree-of-freedom tower crane system; the self-adaptive anti-swing obstacle avoidance feedback controller is constructed by taking target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control targets, and the method comprises the following steps: converting a tower crane obstacle avoidance problem into a state constraint problem; constructing a swing constraint term, an obstacle avoidance constraint term, a physical limitation constraint term, a speed limitation constraint term and an auxiliary term used for describing uncertain parameters and external interference in the system; wherein an auxiliary item of the tower crane is approximated by using a radial basis function neural network, and an approximated network weight matrix is optimized according to an update rate; the controller is used for controlling the rotation angle of a cantilever of the tower crane and the displacement of a trolley on the cantilever, so that safe, effective, accurate and rapid anti-swing obstacle-avoiding movement control is realized.

Description

Technical Field

[0001] The invention relates to the technical field of electromechanical system control, and in particular to a tower crane adaptive anti-sway obstacle avoidance feedback control method and system based on a neural network. Background Art

[0002] In actual construction sites or ports, tower cranes (referred to as tower cranes) play an important role due to their high operating efficiency, large working space and strong payload capacity. In actual construction sites, obstacles such as buildings and heavy equipment will inevitably appear, which poses a huge challenge to the safe and efficient operation of cranes. At present, tower cranes are still mainly operated manually and rely on the experience of operators for control. They have problems such as low working efficiency, poor anti-swing ability and high accident risk. Therefore, it is of great significance to study effective automatic control systems for tower cranes. In fact, during the transportation process using tower cranes, the acceleration or deceleration of the trolley (or trolley) or cantilever may cause the attached cargo to swing due to inherent inertia, thereby reducing transportation efficiency and bringing safety hazards. However, due to the inherent under-driven characteristics, strong coupling and high nonlinearity of tower cranes, the design of anti-swing control systems is very difficult. In addition, even if the cargo swing is effectively suppressed, the cargo may still collide with obstacles on the transportation path, bringing accident risks. Therefore, how to design an effective control method to achieve automatic obstacle avoidance while ensuring accurate positioning and eliminating swing is a severe challenge.

[0003] In order to avoid collisions with obstacles, current research mostly uses heuristic path planning algorithms for mobile robots to design collision-free path planning methods for cranes, such as using particle swarm optimization algorithms, RRT path planning algorithms, probabilistic roadmap algorithms, and A* algorithms to generate collision-free paths for cranes. Although these heuristic path planning algorithms can provide the best collision-free lifting path for cranes, they do not take into account the under-actuated characteristics of cranes and the actual need to suppress swings. Furthermore, there are also studies that mainly use trajectory planning methods to solve the obstacle avoidance and swing suppression problems at the same time, such as a trajectory planning algorithm for a rotary crane based on a dichotomy method, an optimized controller for a collision-free strategy for a double-line hammer crane, and an adaptive input shaper for a tower crane with obstacle avoidance.

[0004] The obstacle avoidance algorithms / methods of various cranes have achieved good results in suppressing swing and avoiding obstacles. However, these methods require a lot of time to solve the motion trajectory. Even in the same construction environment, if the starting position and target position change, the motion trajectory needs to be replanned, resulting in a waste of time. In addition, due to the lack of state feedback, these methods are not very robust to external interference and parameter uncertainty, which may lead to safety hazards and accidents. Summary of the invention

[0005] To address the deficiencies of the above-mentioned prior art, the present invention provides a tower crane adaptive anti-sway obstacle avoidance feedback control method and system based on a neural network. By utilizing the coupling characteristics of the tower crane, the obstacle avoidance task is converted into a state constraint control problem, and a plurality of state constraint auxiliary items are designed to limit the load and trolley positions within a collision-free range, thereby achieving load obstacle avoidance and safe operation. At the same time, a neural network is used to approximate the uncertain / unknown dynamics of the crane system, thereby constructing an adaptive anti-sway obstacle avoidance feedback controller, which is used to control the operation of the tower crane. At the same time, key control problems oriented to practical applications, including obstacle avoidance, uncertain interference, state constraints and nonlinear dynamics, are solved, thereby achieving precise positioning, rapid suppression of swing and obstacle avoidance. The entire control process is safe and effective, with shorter transportation time and stronger robustness to unknown interference.

[0006] In a first aspect, the present invention provides a tower crane adaptive anti-sway obstacle avoidance feedback control method based on a neural network.

[0007] A tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network, comprising:

[0008] Using the Lagrangian method, the dynamic model of the four-degree-of-freedom tower crane system is established;

[0009] Based on the dynamic model, an adaptive anti-sway obstacle avoidance feedback controller is constructed with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: transforming the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate;

[0010] The controller is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley to achieve anti-sway and obstacle avoidance movement control.

[0011] In a second aspect, the present invention provides a tower crane adaptive anti-sway obstacle avoidance feedback control system based on a neural network.

[0012] A tower crane adaptive anti-sway obstacle avoidance feedback control system based on neural network, comprising:

[0013] Model building module, used to build the dynamic model of the four-degree-of-freedom tower crane system using the Lagrangian method;

[0014] A controller construction module is used to construct an adaptive anti-sway obstacle avoidance feedback controller based on a dynamic model with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: converting the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms, as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate;

[0015] The control module is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley using the controller to achieve anti-sway and obstacle avoidance movement control.

[0016] In a third aspect, the present invention further provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps of the method described in the first aspect are completed.

[0017] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the method described in the first aspect.

[0018] One or more of the above technical solutions have the following beneficial effects:

[0019] 1. The present invention provides a tower crane adaptive anti-sway obstacle avoidance feedback control method and system based on neural network. By utilizing the coupling characteristics of tower crane, the obstacle avoidance task is transformed into a state constraint control problem, and multiple state constraint auxiliary items are designed to limit the load and trolley positions within the collision-free range to achieve load obstacle avoidance, and control the trolley and cantilever within the range of motion and speed limit to achieve safe operation. At the same time, the neural network is used to approximate the uncertain / unknown dynamics of the crane system, so as to construct an adaptive anti-sway obstacle avoidance feedback controller, which is used to control the tower crane operation, and solves key control problems such as obstacle avoidance, uncertain interference, state constraints and nonlinear dynamics, which are oriented to practical applications, to achieve precise positioning, rapid suppression of swing and obstacle avoidance. The entire control process is safe and effective, with shorter transportation time and stronger robustness to unknown interference. On this basis, the convergence and stability of the proposed control method and system are theoretically proved by using Lyapunov stability theory, and the effectiveness of the proposed controller is verified by hardware experiments. Compared with the existing methods, under the same external interference and uncertainty, the proposed method can reduce 70% of the transportation time and greatly improve the transportation efficiency.

[0020] 2. In the present invention, based on the nonlinear feedback control method, the tower crane obstacle avoidance problem is transformed into a tower crane state constraint problem. Based on the constructed state constraint terms, the nonlinear controller can restrict the trolley and the boom to a collision-free area to achieve obstacle avoidance, rather than tracking a collision-free reference trajectory. This approach eliminates the need for motion trajectory planning and significantly improves transportation efficiency.

[0021] 3. In the present invention, according to the coupling characteristics of the tower crane, an under-actuated swing constraint item is designed to limit the load swing angle within a predetermined range to avoid the load swing colliding with obstacles, and the swing constraint item also effectively suppresses the load swing during transportation.

[0022] 4. The present invention introduces a radial basis function (RBF) neural network into the designed control method to approximate the uncertain / unknown dynamic function, which effectively improves the positioning accuracy of the trolley / cantilever, improves the robustness of the controller to external interference and uncertain parameters, and improves the safety performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 It is a structural schematic diagram of a tower crane in an embodiment of the present invention;

[0025] Figure 2 Schematic diagram of a tower crane adaptive anti-sway obstacle avoidance feedback control method in an embodiment of the present invention;

[0026] Figure 3 A comparison chart of anti-sway test results of the control method (solid line) and the sliding mode control method (dashed line) described in the embodiment of the present invention;

[0027] Figure 4 The figures are the obstacle avoidance experiment results of the control method (solid line) and the trajectory planning method (dashed line) described in the embodiment of the present invention, wherein (a) is the obstacle avoidance route, and (b) is the result of the tower crane state variable;

[0028] Figure 5 Schematic diagram of the obstacle avoidance experiment results of the control method described in an embodiment of the present invention in a multi-obstacle environment, wherein (a) is an obstacle avoidance route map in different obstacle environments, and (b) is the change of state variables in different obstacle environments. DETAILED DESCRIPTION

[0029] It should be noted that the following detailed descriptions are exemplary only, are intended to describe specific embodiments, are intended to provide further explanation of the present invention, and are not intended to limit exemplary embodiments according to the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art to which the present invention belongs. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0030] Embodiment 1

[0031] This embodiment provides a tower crane adaptive anti-sway obstacle avoidance feedback control method based on a neural network, the method comprising:

[0032] Using the Lagrangian method, the dynamic model of the four-degree-of-freedom tower crane system is established;

[0033] Based on the dynamic model, an adaptive anti-sway obstacle avoidance feedback controller is constructed with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: transforming the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate;

[0034] The controller is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley to achieve anti-sway and obstacle avoidance movement control.

[0035] The following content introduces the adaptive anti-sway obstacle avoidance feedback control method of tower crane based on neural network proposed in this embodiment in more detail.

[0036] In the method proposed in this embodiment, an adaptive anti-sway obstacle avoidance feedback controller is first constructed, and then the controller is used to control the tower crane to achieve anti-sway obstacle avoidance movement. Among them, the construction and application of the controller are the key points of this embodiment, which specifically include:

[0037] (1) The dynamic model of the four-degree-of-freedom tower crane system is established using the Lagrangian method, and on this basis, the analysis is carried out based on this module. The constructed dynamic model includes two driven state quantities and two non-driven state quantities. The driven state quantity includes the cantilever rotation angle and the trolley displacement on the cantilever, and the non-driven state quantity includes the swing angle of the load pulled by the trolley in three-dimensional space, which includes the swing angle θ1 of the load in the horizontal direction of the cantilever and the swing angle θ2 of the load in the vertical direction of the cantilever.

[0038] Specifically, Figure 1 The schematic diagram of the tower crane structure in a three-dimensional environment is shown in FIG. The relevant physical parameters and definitions of the tower crane system are shown in Table 1 below.

[0039] Table 1 Relevant physical parameters and definitions of tower crane system

[0040]

[0041] Based on the Lagrangian method, the dynamic equation of the kinematic model of a three-dimensional four-degree-of-freedom tower crane is established as follows:

[0042]

[0043]

[0044] To simplify the expression, the above kinetic equations (1) to (4) can be simplified into the following matrix form:

[0045]

[0046] in,

[0047]

[0048] In the above equation, the state variable Driven by the term vector and underactuated vector Composition, M(q), and G(q) are the inertia matrix, Coriolis matrix and gravity vector respectively; is the control input vector, where The specific expressions in the above matrices are:

[0049]

[0050] in,

[0051] m 11 =ml 2 (sin 2 θ1cos 2 θ2+sin 2 θ2)+2mlβsinθ1cosθ2+(m+M)β 2 +J,m 12 =-ml2sinθ2,

[0052] m 13 =-ml 2 cosθ1sinθ2cosθ2,m 14 =ml(cosθ2β+lsinθ1),m 22 =M+m,m23 = mlcosθ1cosθ2

[0053] m 24 =-mlsinθ1sinθ2,m 33 =ml 2 cos 2 θ2,m 34 =0,m 44 =ml 2 (8)

[0054]

[0055] Considering that the load is usually under the crane boom, the following assumptions are made:

[0056] θ i ∈(-π2,π2),i=1,2. (10)

[0057] (2) Based on the kinematic model of the tower crane, an adaptive anti-sway obstacle avoidance feedback controller is constructed with target positioning, sway suppression, sway angle constraint, obstacle avoidance, motion area constraint and speed constraint as the control objectives. In this construction process, first, the obstacle avoidance problem of the tower crane is transformed into a state constraint problem, that is, according to the geometric relationship between the load (also called load), the trolley (i.e., the trolley) and the obstacle, the motion constraint ranges of the trolley and the load are generated respectively to ensure that the load moves without collision.

[0058] In this embodiment, an adaptive nonlinear controller is designed to achieve positioning, anti-sway and obstacle avoidance in the presence of parameter uncertainty and external disturbances, and to ensure the safe operation of the trolley and cantilever as the actuator. Specifically, the control objectives can be divided into the following six subtasks:

[0059] (2.1) Accurate target positioning. The controller controls the cantilever to rotate to the target angle position α within the set time. d and the console area moves to the target position β d , its mathematical expression is:

[0060]

[0061] Here, t represents time.

[0062] (2.2) Swing suppression. The controller suppresses the remaining swing of the effective load to 0 when the load reaches the target position within the set time. That is, when the effective load reaches the target position, the remaining swing of the effective load is suppressed, which can be described mathematically as:

[0063]

[0064] (2.3) Swing angle constraint. The controller controls the load (i.e., the load) swing angle within a set safety range, which refers to the range between 0 and the maximum amplitude swing angle, that is:

[0065]

[0066] in, is the maximum amplitude swing angle of θ1(t) and θ2(t).

[0067] (2.4) Obstacle avoidance. The controller controls the Euclidean distance between the load and the obstacle to be greater than or equal to the radius of the obstacle enclosure. That is, during transportation, the load and the trolley should avoid collision with obstacles. The mathematical expression is:

[0068]

[0069] Among them, ω i Represents the radius of the obstacle enclosing box, satisfying ω i >lsinθ m +r i ρ i (x,y) is the effective load and i th The Euclidean distance between obstacles is defined as:

[0070]

[0071] Among them, x = βcosα and y = βsinα are the horizontal and vertical coordinates of the car, (x obs,i ,y obs,i ) and r i is i th The center coordinates and radius of the obstacle.

[0072] Combined with the swing angle constraint defined above, when the maximum swing angle of the load is θ m When , according to the geometric relationship between the load and the trolley, the maximum distance between the load and the trolley is lsinθ m To ensure that the payload does not collide with obstacles due to unexpected swings, i As i th The radius of the circular bounding box of the obstacle should satisfy the constraint condition: ω i >lsinθ m +r i That is, when the distance between the trolley and the obstacle center is at least ω and the maximum swing angle of the load does not exceed θ m When the load is moved, it can be ensured that it does not collide with obstacles.

[0073] (2.5) Motion range constraint. The controller controls the actuator (i.e., the trolley and the cantilever) and restricts it to move within a specific range, defined as:

[0074] α min <α<α max ,β min <β<β max (16)

[0075] Among them, α min , α max , β min , β max They are the upper and lower bounds of the physical limitations of the cantilever and the car, respectively.

[0076] (2.6) Speed ​​constraint. The controller controls the actuator (i.e., the trolley and the cantilever) and limits its movement speed to a safe speed range, which is defined as:

[0077]

[0078] in, are the boundaries of the cantilever and trolley speed limits respectively.

[0079] (3) Secondly, obstacle avoidance constraints, swing angle constraints, physical restriction constraints, and speed restriction constraints are constructed. The constructed swing constraint and obstacle avoidance constraints are used as the nonlinear control part of the controller to restrict the trolley to the obstacle-free area and the swing angle to the preset range, respectively, to achieve swing angle constraint and obstacle avoidance; similarly, the constructed physical restriction constraint and speed restriction constraints are used as the nonlinear control part of the controller to restrict the trolley and cantilever to the physical restriction area (such as track length restriction, construction area restriction, etc.) and the movement speed safety range, respectively, to achieve safe operation of the trolley and cantilever. By introducing the above constraints, the controller can automatically drive the trolley and payload to effectively avoid obstacles in the workspace, prevent the actuator from exceeding the physical restriction area, and ensure that the operating speed of the actuator is within the safe range, thereby achieving automatic obstacle avoidance and safe operation.

[0080] Specifically, the construction of the above swing constraint term, obstacle avoidance constraint term, physical limit constraint term and speed limit constraint term is as follows: construct an error term according to the target value and actual value of the swing angle of the load in three-dimensional space; based on the error term, construct the swing constraint term, obstacle avoidance constraint term, physical limit constraint term and speed limit constraint term, such as Figure 2 As shown, including:

[0081] First, define the error term and its derivative Its specific expression is:

[0082]

[0083] In the above formula, α d , βd Represent the target positions of the cantilever and the car respectively.

[0084] In order to solve the obstacle avoidance and swing elimination problems of tower cranes, the following auxiliary constraints are constructed to achieve obstacle avoidance and load swing angle constraints:

[0085] (3.1) Constructing the swing constraint term Limit the load swing angle to a certain range, defined as:

[0086]

[0087] (3.2) Constructing obstacle avoidance constraints Defined as:

[0088]

[0089] In the above formula, k c is the obstacle avoidance parameter of the tower crane, which can be adjusted according to the actual usage. For the convenience of representation, the obstacles in this embodiment are all represented by the enclosing circle of the obstacle, that is, the obstacle is represented by a circle enclosing the obstacle, and ω represents the radius length of the enclosing circle, which can ensure that the car will not enter the enclosing circle area.

[0090] (3.3) Constructing physical constraints Confine the cart and cantilever to the limits imposed by the physical constraints, defined as:

[0091]

[0092] In the above formula, k wα and k wβ It is a physical limiting parameter that determines the size of the limiting force and can be adjusted according to actual usage.

[0093] (3.4) Construct the speed limit constraint of the actuator Limit the actuator speed to a specific interval, defined as:

[0094]

[0095] In the above formula, k rα and k rβ It is a speed limit parameter and can be adjusted according to actual usage.

[0096] (4) Construct auxiliary items for describing uncertain parameters and external interference in the system, and use radial basis function RBF neural network to approximate the auxiliary items of the tower crane, and optimize the approximate network weight matrix according to the update rate. In this embodiment, the radial basis function RBF neural network is introduced into the control to deal with parameter uncertainty and external interference, especially to eliminate the influence of uncertain parameters on obstacle avoidance constraint items and swing angle constraint items, ensure the accuracy of obstacle avoidance, effectively improve the positioning accuracy of the trolley and the cantilever, and improve the robustness of the control system.

[0097] Specifically, for stability analysis, an auxiliary term Φ is proposed, which is defined as:

[0098]

[0099] in, is the identity matrix, Φ0 is a known nominal value, Φ Δ is the unknown part of the crane system. The unknown / unavailable parameters / structure of the tower crane are approximated using the radial basis function (RBF) neural network, which is expressed as:

[0100]

[0101] in, is the input of the neural network, To satisfy The approximation error, W * is the optimal weight matrix, which can be expressed as:

[0102]

[0103] In addition, φ(x) represents an activation function vector. In this embodiment, the following Gaussian function is selected and expressed as:

[0104]

[0105] Among them, c represents the center vector and b represents the standard deviation vector.

[0106] Furthermore, the controller constructed in this embodiment can be expressed as:

[0107]

[0108] in, Defined as K p , K z , K d , K A , K I , is a diagonal matrix with positive control gains, W *The estimated matrix of , the update rate of which is:

[0109]

[0110] Here, Γ represents a diagonal matrix with positive parameters.

[0111] In addition, some control gains in the controller also meet the following conditions:

[0112]

[0113] Finally, in order to prove the stability of the controller constructed above, the following Lyapunov function is designed, and the stability and convergence of the proposed controller are verified by using the Lyapunov function. The function is:

[0114]

[0115] Taking the derivative of the above Lyapunov function, we get:

[0116]

[0117] in, Can be arranged in the following matrix form:

[0118]

[0119] According to the kinetic equation, we can get:

[0120]

[0121] therefore, It can be deduced that:

[0122]

[0123] After that, by plugging in the designed controller and update rate, we get:

[0124]

[0125] Therefore, it can be deduced that:

[0126]

[0127] Based on the above calculation results, it can be clearly seen that as long as the initial swing angles θ1(0) and θ2(0) are within the preset range (-θ m ,θ m ), then there must exist a time T with Assuming that the swing angle tends to exceed the preset range, there must be driving variables θ1(T) and θ2(T) close to the preset boundary, which makes V(t) or When time approaches infinity, we can conclude that: V(t)→+∞, which is consistent with the result Therefore, during the entire control process, the load displacements θ1 and θ2 will not exceed the preset range, that is:

[0128]

[0129] Similarly, if the initial position of the car is within the preset range, A α and A β Will follow ρ i (x,y)→ω i tends to infinity, that is, V(t)→+∞, which is consistent with the conclusion Instead, therefore, there is:

[0130] ρ i (α(t),y(t))≥ω i (42)

[0131] It can be further confirmed that the swing angle and the trolley will only be in a specific area to ensure that the load will not collide with obstacles.

[0132] Similarly, if the car and the cantilever approach the physical restriction area α max and β max , then there must be V(t)→+∞, which is consistent with the conclusion Contradictory, therefore, we have:

[0133] α min <α<α max ,β min <β<β max (43)

[0134] Next, integrating (39) yields:

[0135]

[0136] Two situations are discussed here:

[0137] The first case: When When , suppose there is a time t∈[T1,T2], if there is a point Approaching the speed limit and Then there must be:

[0138]

[0139] This contradicts the conclusion of formula (39), so the speed of the actuator will never exceed the set value, that is, the speed must be within the set range. Inside.

[0140] The second situation: When When the actuator speed is within the set range Inside.

[0141] Therefore, combining the above two situations, it can be concluded that the actuator speed will not exceed the set area, that is:

[0142]

[0143] Furthermore, to prove that the state variables converge to the target value at the equilibrium point, an invariant set is defined as:

[0144]

[0145] An invariant set has a maximal invariant subset exist In, there are:

[0146]

[0147] In addition, it also includes:

[0148]

[0149] Similarly, the following results can be obtained:

[0150]

[0151] According to the dynamic expression and controller, the following results can be obtained:

[0152] T=0,F=0 . (51)

[0153] Therefore, the underactuated part (i.e., non-actuated part) of the dynamic equation can be written as:

[0154]

[0155] Substituting the above two equations into the driving part of the dynamic equation, we can get:

[0156]

[0157] Then we can get:

[0158]

[0159] Afterwards, according to and cosθ2>0,cosθ1>0, we can get:

[0160]

[0161] Similarly, we can get:

[0162]

[0163] Therefore, according to the above conclusion, it can be concluded that only the equilibrium point of the closed-loop system is in the subset S ,Therefore, it can be guaranteed that the tower crane can complete the transportation task, avoid obstacles, and the swing angle is 0 after the load reaches the target position.

[0164] Furthermore, in order to ensure the effectiveness of the method proposed in this embodiment, it is compared with the existing synovial control method. Figure 3 As shown in the figure, both methods can achieve fast and accurate rotation / translation positioning and effective swing suppression, and it takes about 10 seconds for the rotating arm and the car to reach the target and remain stable. However, the controller proposed in this embodiment can achieve more accurate positioning and a smaller residual swing angle; in addition, the proposed method shows superior performance in terms of energy consumption, especially in terms of the energy consumption of the rotating arm movement; and the method proposed in this embodiment has no obvious residual swing and is safer, while the comparative sliding mode control method has obvious residual swing, which means that when reaching the target point, the comparative method still has swing, which may cause unexpected collisions.

[0165] In order to verify the obstacle avoidance performance of the method proposed in this embodiment, the effectiveness of this method is verified by comparing it with the trajectory planning method. Figure 4 As shown in (a), the two obstacles are represented by circles. It can be seen that both methods can effectively avoid obstacles and accurately reach the target position. However, the trajectory planning method requires a lot of offline solution time. Combined with (b), this method significantly reduces the transportation time by 70% in the computing platform of Intel Core-i5 CPU 3.6GHz×4and RAM of 16GB, which includes offline calculation time.

[0166] Finally, obstacle avoidance experiments were conducted in a multi-obstacle environment. Figure 5 As shown in (a) and (b), it can be seen that the method can effectively avoid multiple obstacles while transporting the load to the target point, and effectively suppress the swing. During the entire transportation process, the swing of the load does not exceed the limit value. After reaching the target point, the method proposed in this embodiment almost does not involve swinging, ensuring the stability and safety of tower crane transportation.

[0167] That is, compared with the sliding film controller and trajectory planning method in the prior art, the controller and control method proposed in this embodiment have higher positioning accuracy and more effective anti-sway performance.

[0168] Embodiment 2

[0169] This embodiment provides a tower crane adaptive anti-sway obstacle avoidance feedback control system based on a neural network, including:

[0170] Model building module, used to build the dynamic model of the four-degree-of-freedom tower crane system using the Lagrangian method;

[0171] A controller construction module is used to construct an adaptive anti-sway obstacle avoidance feedback controller based on a dynamic model with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: converting the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms, as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate;

[0172] The control module is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley using the controller to achieve anti-sway and obstacle avoidance movement control.

[0173] Embodiment 3

[0174] This embodiment provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, the steps in the adaptive anti-sway obstacle avoidance feedback control method for tower crane based on neural network as described above are completed.

[0175] Embodiment 4

[0176] This embodiment also provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps in the above-mentioned adaptive anti-sway obstacle avoidance feedback control method for tower crane based on neural network are completed.

[0177] The steps involved in the above embodiments 2 to 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0178] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0179] The above description is only a preferred embodiment of the present invention. Although the specific implementation mode of the present invention is described in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present invention, various modifications or deformations that can be made by technical personnel in this field without creative work are still within the scope of protection of the present invention.

Claims

1. A tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network, characterized in that: include: Using the Lagrangian method, the dynamic model of the four-degree-of-freedom tower crane system is established; Based on the dynamic model, an adaptive anti-sway obstacle avoidance feedback controller is constructed with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: transforming the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate; The controller is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley to achieve anti-sway and obstacle avoidance movement control.

2. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network according to claim 1, characterized in that: The constructed dynamic model includes driven state quantities and non-driven state quantities, wherein the driven state quantities include the cantilever rotation angle and the trolley displacement on the cantilever, and the non-driven state quantities include the swing angle of the load pulled by the trolley in three-dimensional space, which includes the swing angle of the load in the horizontal direction of the cantilever and the swing angle of the load in the vertical direction of the cantilever.

3. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network as claimed in claim 1, characterized in that: The target positioning control target is to control the cantilever to rotate to the target angle position and the control console area to move to the target position within the set time; The swing suppression control target is to suppress the remaining swing of the effective load to 0 when the load reaches the target position within the set time; The swing angle constraint control target is to control the load swing angle within a set safety range, which is the range between 0 and the maximum amplitude swing angle; The obstacle avoidance control goal is to control the Euclidean distance between the load and the obstacle to be greater than or equal to the radius of the obstacle enclosing box; The motion area constraint control objective is to restrict the movement of the trolley and cantilever as actuators within a specific range; The speed constraint control objective is to limit the movement speed of the trolley and cantilever as actuators within a safe speed range.

4. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network as claimed in claim 1, characterized in that: The swing constraint term and obstacle avoidance constraint term are used as nonlinear control parts of the controller to respectively restrict the car to an obstacle-free area and restrict the swing angle to a preset range, so as to realize the swing angle constraint and obstacle avoidance; The physical restriction constraint item and the speed restriction constraint item serve as the nonlinear control part of the controller, which respectively restrict the trolley and the cantilever to operate within the physical restriction area and the safe speed range, so as to realize the safe operation of the trolley and the cantilever.

5. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network as claimed in claim 4, characterized in that: The construction of the swing constraint item, obstacle avoidance constraint item, physical restriction constraint item and speed restriction constraint item includes: According to the target value and actual value of the load's swing angle in three-dimensional space, an error term is constructed; Based on the error term, the swing constraint term, obstacle avoidance constraint term, physical limitation constraint term and speed limit constraint term are constructed.

6. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network according to claim 1, characterized in that: The radial basis function (RBF) neural network is used to approximate the auxiliary items of the tower crane, which can be expressed as: In the above formula, is the input of the neural network, To satisfy The approximation error, W * is the optimal weight matrix, φ(x) represents the activation function vector.

7. The tower crane adaptive anti-sway obstacle avoidance feedback control method based on neural network as claimed in claim 1, characterized in that: The controller is represented as: In the above formula, Defined as K p , K z , K d , K A , K I , is a diagonal matrix with positive control gains, W * The estimated matrix of , the update rate of which is: Γ represents a diagonal matrix with positive parameters.

8. A tower crane adaptive anti-sway obstacle avoidance feedback control system based on neural network, characterized in that: include: Model building module, used to build the dynamic model of the four-degree-of-freedom tower crane system using the Lagrangian method; A controller construction module is used to construct an adaptive anti-sway obstacle avoidance feedback controller based on a dynamic model with target positioning, swing suppression, swing angle constraint, obstacle avoidance, motion area constraint and speed constraint as control objectives; the construction includes: converting the tower crane obstacle avoidance problem into a state constraint problem, constructing swing constraint terms, obstacle avoidance constraint terms, physical restriction constraint terms and speed restriction constraint terms, as well as auxiliary terms for describing uncertain parameters and external interference in the system; wherein, the auxiliary terms of the tower crane are approximated by using a radial basis function (RBF) neural network, and the approximate network weight matrix is ​​optimized according to the update rate; The control module is used to control the cantilever rotation angle of the tower crane and the displacement of the cantilever upper trolley using the controller to achieve anti-sway and obstacle avoidance movement control.

9. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of a tower crane adaptive anti-sway obstacle avoidance feedback control method based on a neural network as described in any one of claims 1 to 7 are completed.

10. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of a tower crane adaptive anti-sway obstacle avoidance feedback control method based on a neural network as described in any one of claims 1-7.

Images