Power distribution network hot-line work intelligent equipment control method based on sliding mode control

Abstract

The invention relates to the technical field of electrical automation, and discloses a sliding mode control-based power distribution network hot-line work intelligent equipment control method, which comprises the steps of optimizing a dynamic model of N-joint hot-line work intelligent equipment, and constructing an error dynamic model. Meanwhile, a linear expansion state observer is designed for real-time observation compensation for unknown items and uncertain items in the N-joint hot-line work intelligent equipment tracking error dynamic model. The design of the neural network self-adaptive global nonsingular terminal sliding mode controller can ensure finite time convergence, avoid singular phenomena, enhance robustness and realize high-precision tracking control while parameter self-adaption is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical automation, and in particular to a method for controlling intelligent equipment for live working in a distribution network based on sliding mode control. Background Art

[0002] Bionic live-working intelligent equipment has the characteristics of adaptability to narrow spaces, diverse movement forms, fault resistance, high-precision inspection and reduced human resource consumption. It can move flexibly in a small space, such as the narrow gaps between power towers or the complex truss structure of cables. The ability to change its body shape helps the robot climb power towers, cross cable trenches and other complex terrains to complete inspection tasks. Failures in a certain link will not affect the completion of the entire task. It is equipped with a rich set of sensors to reduce human errors and improve inspection accuracy.

[0003] However, in actual situations, the modeling of intelligent equipment for simulating live working is complex and difficult to solve. It is often difficult to use complex control algorithms to efficiently track and control them. Some simple control algorithms are difficult to control with high precision. Therefore, the optimization of the model and the design of high-precision control algorithms are crucial for the control of intelligent equipment for simulating live working. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a control method for intelligent equipment for live working in a distribution network based on sliding mode control, and proposes a neural network adaptive global nonlinear terminal sliding film control method based on a linear extended state observer while optimizing mathematical modeling.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: including, based on the dynamic model of N-joint live working intelligent equipment, reconstructing the tracking error dynamic model of N-joint live working intelligent equipment; designing a linear extended state observer to observe and compensate the unknown items and uncertain items in the tracking error dynamic model of N-joint live working intelligent equipment in real time; constructing a global non-singular terminal sliding surface based on the characteristics of terminal sliding mode finite time arrival, non-singular avoidance of convergence stagnation, and global sliding mode quickly reaching the sliding surface; designing a neural network adaptive constant speed approach rate based on the constructed global non-singular terminal sliding surface; combining the linear extended state observer, the global non-singular terminal sliding surface and the neural network adaptive constant speed approach rate, designing a neural network adaptive global non-singular terminal sliding mode controller based on the linear extended state observer for the N-joint live working intelligent equipment system.

[0008] As a preferred solution of the control method of the live-line working intelligent equipment of the distribution network based on sliding mode control described in the present invention, wherein: the tracking error dynamics model of the N-joint live-line working intelligent equipment is reconstructed, including:

[0009] The dynamic model of the N-joint live working intelligent device is as follows:

[0010]

[0011] Among them, q φ =[φ1,…,φ N-1 ,φ N ,p x ,p y ] T ∈R (N+2)×1 ,φ i is the i-th joint angle of the live working intelligent device, (p x ,p y ) is the centroid coordinate of the live working intelligent device; M(φ)∈R (N+2)×(N+2) is the inertia matrix of the system, is the Coriolis and centripetal force matrix, G(φ)∈T (N+2)×2N and are the gravity and friction matrices, u is the joint input torque, u=[u1,…,u N-1 ,0,0,0] T ∈R (N+2)×1 .

[0012] The tracking error of the N-joint live working intelligent device is defined as:

[0013]

[0014] in, is the target trajectory of the N-joint live working intelligent device; q φ (t) is the actual trajectory of the N-joint live-line working intelligent device; e(t)∈R (N+2)×1 is the tracking error of the N-joint live working intelligent device.

[0015] The second-order differential of the tracking error of the N-joint live working intelligent device is:

[0016]

[0017] in, is the second-order differential of e(t), yes The second-order differential of Yes φ The second-order differential of (t).

[0018] definition Matrix, the dynamic model of the N-joint live working intelligent equipment is changed as follows:

[0019]

[0020] in, is the dimensionless parameter gain matrix,

[0021] Bring in the second-order differential of the tracking error to build a dynamic model of the tracking error of the N-joint live-working intelligent equipment:

[0022]

[0023] As a preferred solution of a control method for intelligent equipment for live working in a distribution network based on sliding mode control described in the present invention, a linear extended state observer is designed, including:

[0024] The linear extended state observer is defined as follows:

[0025]

[0026] Among them, z1 is the actual trajectory q of the N-joint live working intelligent device φ (t), z2 is the observed value of F(t) for uncertain terms and unknown disturbances in the dynamic model of the N-joint live-line working intelligent equipment, e1=z1(t)-q φ (t) is the observation error of the linear extended state observer to the actual output trajectory.

[0027] As a preferred solution of the control method of the intelligent equipment for live working in the distribution network based on sliding mode control described in the present invention, wherein: a global non-singular terminal sliding mode surface is designed, including:

[0028] The global non-singular terminal sliding surface is designed as:

[0029]

[0030]

[0031] Among them, ηe(t) is the tracking error proportional term of the N-joint live-working intelligent device, and η is the proportional term parameter adjustment gain; is a non-singular term, ω, and σ are non-singular parameter adjustment gains, which must satisfy: and σ is a positive odd number.

[0032] The first-order differential of the global non-singular terminal sliding surface is as follows:

[0033]

[0034] in, is the first-order differential of s(t) with respect to time t, They are s1(t),s2(t),…,s N (t),S N+1 (t),s N+2 (t)The first-order differential with respect to time t.

[0035] As a preferred solution of the control method of intelligent equipment for live working in distribution network based on sliding mode control described in the present invention, wherein: the adaptive constant speed approach rate of the neural network is designed, including:

[0036] The adaptive constant speed approach rate is designed as follows:

[0037]

[0038] in, is the adaptive term parameter of the constant velocity approach rate,

[0039] As a preferred solution of the method for controlling intelligent equipment for live working in distribution network based on sliding mode control described in the present invention, it also includes:

[0040] The neural network adaptation rate is designed as:

[0041]

[0042] in, is the constant approach rate adaptive term parameter is the approximate value of , ζ is the control gain of the adaptive rate, h(x) is the hidden layer activation function of the neural network observer, is the optimal weight of the neural network from the hidden layer to the output layer, and Γ is between and The approximate error of It is W * The estimated value of yes The adaptation rate.

[0043] The hidden layer activation function is chosen as the cubic B-spline basis function, which is defined as:

[0044] h(x)=[h1(t),h2(t),…,h N (t),h N+1 (t),h N+2 (t)]

[0045]

[0046] When ‖xo i ||≤h i When i=1,2…,N+2

[0047]

[0048] When h i <||xo i ||≤2h i When i=1,2…,N+2

[0049]

[0050] When 2h i <||xo i ||, and i=1,2…,N+2

[0051] h i (x) = 0

[0053] Among them, ||xo i || is the distance between the input vector and the center vector in Euclidean form; x is the input vector; o and o i is the center vector; h i is the width of the cubic B-spline function.

[0054] As a preferred solution of the control method of intelligent equipment for live working in distribution network based on sliding mode control described in the present invention, the designed controller includes:

[0055] Combining the linear extended state observer, the global non-singular terminal sliding mode surface and the neural network adaptive constant velocity approach rate, the neural network adaptive global non-singular terminal sliding mode controller of the N-joint live working intelligent equipment system based on the linear extended state observer is designed as follows:

[0056]

[0057] Beneficial effects of the present invention: The present invention optimizes the dynamic model of the N-joint live-working intelligent equipment and constructs an error dynamic model. At the same time, the linear extended state observer is used to observe the uncertainties and disturbances so as to compensate them in the constructed error dynamic model system of the live-working intelligent equipment. The design of the adaptive global non-singular terminal sliding mode controller can achieve high-precision tracking control while ensuring finite-time convergence, avoiding singular phenomena and enhancing robustness while achieving parameter adaptation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0059] Figure 1 It is a schematic diagram of the principle control framework of a method for controlling intelligent equipment for live working in a distribution network based on sliding mode control of the present invention;

[0060] Figure 2 A comparison diagram of tracking effects of a neural network adaptive global non-singular terminal sliding mode control method (SMC) and a traditional PID control method (PID) for a joint angle 1 of a three-degree-of-freedom live-working intelligent device under a target trajectory 1 (aim1) of a control method for a live-working intelligent device for a distribution network based on sliding mode control of the present invention;

[0061] Figure 3 It is a target trajectory tracking effect diagram of a control method for live-line working intelligent equipment of distribution network based on sliding mode control of the present invention, comparing the joint angle 2 of the three-degree-of-freedom live-line working intelligent equipment under target trajectory 2 (aim2) by a neural network adaptive global non-singular terminal sliding mode control method (SMC) and a traditional PID control method (PID);

[0062] Figure 4 The present invention is a flowchart of a method for controlling intelligent equipment for live working in a distribution network based on sliding mode control. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0066] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0067] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0068] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0069] Example 1

[0070] Reference Figure 1 , Figure 4, which is the first embodiment of the present invention, provides a control method for live-working intelligent equipment in distribution network based on sliding mode control. The method of the present invention is based on the dynamic model of N-joint live-working intelligent equipment, and reconstructs the tracking error dynamic model of N-joint live-working intelligent equipment; for the unknown and uncertain terms in the tracking error dynamic model of N-joint live-working intelligent equipment, a linear extended state observer is designed to observe and compensate in real time; according to the characteristics of terminal sliding mode finite time arrival, non-singularity to avoid convergence stagnation, and global sliding mode quickly reaching the sliding surface, a global non-singular terminal sliding surface is constructed; based on the constructed global non-singular terminal sliding surface, a neural network adaptive constant-speed approach rate is designed to combine the linear extended state observer, the global non-singular terminal sliding surface and the neural network adaptive constant-speed approach rate, and a neural network adaptive global non-singular terminal sliding mode controller based on the linear extended state observer for the N-joint live-working intelligent equipment system is designed;.

[0071] S1: Based on the dynamic model of the N-joint live-line working intelligent device, the tracking error dynamic model of the N-joint live-line working intelligent device is reconstructed. The following points need to be explained in this step:

[0072] The dynamic model of the N-joint live working intelligent device is as follows:

[0073]

[0074] Among them, q φ =[φ1,…,φ N-1 ,φ N ,p x ,p y ] T ∈R (N+2)×1 ,φ i is the i-th joint angle of the live working intelligent device, (p x ,p y ) is the centroid coordinate of the live working intelligent device; M(φ)∈R (N+2)×(N+2) is the inertia matrix of the system, is the Coriolis and centripetal force matrix, G(φ)∈R (N+2)×2N and are the gravity and friction matrices, u is the joint input torque, u=[u1,…,u N-1 ,0,0,0] T ∈R (N+2)×1 .

[0075] The tracking error of the N-joint live working intelligent device is defined as:

[0076]

[0077] in, is the target trajectory of the N-joint live working intelligent device; q φ (t) is the actual trajectory of the N-joint live-line working intelligent device; e(t)∈R (N+2)×1 is the tracking error of the N-joint live working intelligent device.

[0078] The second-order differential of the tracking error of the N-joint live working intelligent device is:

[0079]

[0080] in, is the second-order differential of e(t), yes The second-order differential of Yes φ The second-order differential of (t).

[0081] definition Matrix, the dynamic model of the N-joint live working intelligent equipment is changed as follows:

[0082]

[0083] in, is the dimensionless parameter gain matrix,

[0084] Bring in the second-order differential of the tracking error to build a dynamic model of the tracking error of the N-joint live-working intelligent equipment:

[0085]

[0086] S2: Design a linear extended state observer to observe and compensate for the unknown and uncertain terms in the tracking error dynamics model of the N-joint live working intelligent equipment in real time. The following points need to be explained in this step:

[0087] The linear extended state observer is defined as follows:

[0088]

[0089] Among them, z1 is the actual trajectory q of the N-joint live working intelligent device φ (t), z2 is the observed value of F(t) for uncertain terms and unknown disturbances in the dynamic model of the N-joint live-line working intelligent equipment, e1=z1(t)-q φ (t) is the observation error of the linear extended state observer to the actual output trajectory.

[0090] S3: Based on the characteristics of the terminal sliding mode reaching the sliding mode in a finite time, avoiding convergence stagnation, and the global sliding mode quickly reaching the sliding mode surface, a global non-singular terminal sliding mode surface is constructed. The following points need to be explained in this step:

[0091] The global non-singular terminal sliding surface is designed as:

[0092]

[0093] Among them, ηe(t) is the tracking error proportional term of the N-joint live-working intelligent device, and η is the proportional term parameter adjustment gain; is a non-singular term, ω, and σ are non-singular parameter adjustment gains, which must satisfy: and σ is a positive odd number.

[0094] The first-order differential of the global non-singular terminal sliding surface is as follows:

[0095]

[0096] in, is the first-order differential of s(t) with respect to time t, They are s1(t),s2(t),…,s N (t),s N+1 (t),S N+2 (t)The first-order differential with respect to time t.

[0097] S4: Based on the constructed global non-singular terminal sliding surface, design the neural network adaptive constant velocity approach rate. The following points need to be explained in this step:

[0098] The adaptive constant speed approach rate is designed as follows:

[0099]

[0100] in, is the adaptive term parameter of the constant velocity approach rate,

[0101] The neural network adaptation rate is designed as:

[0102]

[0103] in, is the constant approach rate adaptive term parameter is the approximate value of , ζ is the control gain of the adaptive rate, h(x) is the hidden layer activation function of the neural network observer, is the optimal weight of the neural network from the hidden layer to the output layer, and Γ is between and The approximate error of It is W * The estimated value of yes The adaptation rate.

[0104] The hidden layer activation function is chosen as the cubic B-spline basis function, which is defined as:

[0105] h(x)=[h1(t),h2(t),…,h N (t),h N+1 (t),h N+2 (t)]

[0106]

[0107] When || xo i ||≤h i When i=1,2…,N+2

[0108]

[0109] When h i <||xo i ||≤2h i When i=1,2…,N+2

[0110]

[0111] When 2h i <||xo i ||, and i=1,2…,N+2

[0112] h i (x) = 0

[0114] Among them, ||xo i || is the distance between the input vector and the center vector in Euclidean form; x is the input vector; o and o i is the center vector; h i is the width of the cubic B-spline function.

[0115] S5: Combining the linear extended state observer, the global non-singular terminal sliding mode surface and the neural network adaptive constant velocity approach rate, a neural network adaptive global non-singular terminal sliding mode controller based on the linear extended state observer is designed for the N-joint live working intelligent equipment system. The following should be noted in this step:

[0116] The controller is designed to:

[0117]

[0118] Preferably, it should be noted that, compared with the prior art, this embodiment discloses a control method for live-working intelligent equipment in a distribution network based on sliding mode control, which uses a tracking error dynamics model to replace the complex dynamics model of the actual N joints of the live-working intelligent equipment, so as to simplify the mathematical model in the control process. At the same time, in order to deal with the uncertainties and disturbances in the system, a linear extended state observer is used for real-time compensation feedback. In addition, an adaptive global non-singular terminal sliding mode control method is designed, which not only ensures that the robot can achieve fast and high-precision tracking control, but also that there will be no convergence stagnation problem in the entire control process, thereby effectively ensuring the stability and accuracy of the tracking effect.

[0119] Example 2

[0120] Reference Figure 2-3 , which is another embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a test verification of a control method for a live-line operation intelligent device of a distribution network based on sliding mode control, including:

[0121] In order to verify and illustrate the technical effect adopted in this method, in this embodiment, a traditional PID control method is selected to be compared with the method of the present invention, and the test results are compared by scientific demonstration to verify the real effect of this method.

[0122] The physical parameters of the three-degree-of-freedom live working intelligent equipment are: the joint connecting rod N of the live working intelligent equipment is 4, the mass of a single connecting rod of the live working intelligent equipment is m=0.25kg and the mass of each connecting rod is evenly distributed, the joint length is l=0.08m, and the ground friction force c t =1, c n =10, J = 0.0064 kg × m 2 .

[0123] The vector and inertia matrix used by the three-degree-of-freedom live-line working intelligent equipment system are:

[0124]

[0125] M θ =JI N +ml 2 S θ VS θ +ml 2 C θ VC θ , V = A T (ZZ T ) -1 A; W = ml2 S θ VC θ -ml 2 C θ VS θ ;

[0126] The input and output vectors of the live working intelligent device are respectively φ=[φ1,φ2] T , u=[u1,u2] T The initial condition of the live working intelligent device is φ(0)=[0,0] T rad,

[0127] The target trajectory of joint angle 1 is: The target trajectory of joint angle 2 is: ref2 =sin(πt).

[0128] The parameters of the global fractional-order non-singular terminal sliding mode controller of the present invention are: α=diag(0.564.22.75), β=diag(0.0820.47.53), γ=diag(37425), eta=diag(17.5,20,15,13.5,10), σ=7,h i =[1,2,5,8,1],

[0129] The comparison controller is a traditional PID controller: The comparison controller parameter is k tp =diag(3.5,2.95,0,0,0), k ti =diag(10.25,8.35,0,0,0),k td =diag(0.02.0.015,0,0,0).

[0130] Test environment: Reference Figure 1In the SIMULINK environment of MATLAB 2019a, a controlled object model of live working intelligent equipment is built according to the existing physical quantity parameters and mathematical models of live working intelligent equipment. The control method of live working intelligent equipment with neural network adaptive global terminal sliding mode and the traditional PID control method are used to track and control the drivable joint 1 and drivable joint 2 under different target trajectories and obtain test result data. Both methods will start the automated test equipment and use MATLB software programming to implement simulation tests of the comparison methods. Simulation data are obtained according to the test results. Each method tests 4 groups of data, and each group of data is sampled for 10s. The target trajectory of each group of data input and the tracking trajectory of the output are calculated and compared to verify the feasibility of the proposed algorithm.

[0131] Reference Figure 2 The present invention can drive the joint angle 1 under the target trajectory 1 (aim1) to compare the tracking effect of the neural network adaptive global terminal sliding mode control method (SMC) and the traditional PID control method (PID). Figure 3 The present invention can drive the joint angle 2 under the target trajectory 2 (aim2) to compare the tracking effect of the neural network adaptive global terminal sliding mode control method (SMC) and the traditional PID control method (PID). As can be seen from the figure, the neural network adaptive global terminal sliding mode control method (SMC) and the traditional PID control method (PID) can track the target trajectory 1 (aim1) and the target trajectory 2 (aim2) as a whole. However, from the perspective of convergence speed, steady-state error and stability, the neural network adaptive global terminal sliding mode control method (SMC) is superior to the traditional PID control method (PID) in all aspects. Thanks to the real-time compensation of disturbances and uncertainties by the linear extended state observer and the designed self-neural network adaptive global flying linear terminal sliding film controller, it can globally converge and reach the sliding surface in a limited time and solve the convergence stagnation problem.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for controlling intelligent equipment for live working in a distribution network based on sliding mode control, characterized in that: include, S1. Based on the dynamic model of N-joint live-line working intelligent equipment, the tracking error dynamic model of N-joint live-line working intelligent equipment is reconstructed; S2. Design a linear extended state observer to observe and compensate for the unknown and uncertain terms in the tracking error dynamics model of N-joint live-working intelligent equipment in real time; S3, constructing a global non-singular terminal sliding surface based on the characteristics of the terminal sliding mode reaching the sliding surface in a finite time, avoiding convergence stagnation in a non-singular manner, and the global sliding mode quickly reaching the sliding surface; S4. Based on the constructed global non-singular terminal sliding surface, a neural network adaptive constant velocity approach rate is designed; S5. Combining the linear extended state observer, the global non-singular terminal sliding mode surface and the neural network adaptive constant velocity approach rate, a neural network adaptive global non-singular terminal sliding mode controller based on the linear extended state observer is designed for the N-joint live working intelligent equipment system.

2. According to the method for controlling intelligent equipment for live working in distribution network based on sliding mode control in claim 1, it is characterized in that: The dynamic model of the S1 N-joint live working intelligent device is as follows: Among them, q φ =[φ1,…,φ N-1 ,φ N ,p x ,p y ] T ∈R (N+2)×1 ,φ i is the i-th joint angle of the live working intelligent device, (p x ,p y ) is the centroid coordinate of the live working intelligent device; M(φ)∈R (N+2)×(N+2) is the inertia matrix of the system, is the Coriolis and centripetal force matrix, G(φ)∈R (N+2)×2N and are the gravity and friction matrices, u is the joint input torque, u=[u1,…,u N-1 ,0,0,0] T ∈R (N+2)×1 ; The tracking error of the N-joint live working intelligent device is defined as: in, is the target trajectory of the N-joint live working intelligent device; q φ (t) is the actual trajectory of the N-joint live-line working intelligent device; e(t)∈R (N+2)×1 is the tracking error of the N-joint live working intelligent device; The second-order differential of the tracking error of the N-joint live working intelligent device is: in, is the second-order differential of e(t), yes The second-order differential of Yes φ The second-order differential of (t); definition Matrix, the dynamic model of the N-joint live working intelligent equipment is changed as follows: in, is the dimensionless parameter gain matrix, Bring in the second-order differential of the tracking error to build a dynamic model of the tracking error of the N-joint live-working intelligent equipment:

3. A method for controlling intelligent equipment for live working in a distribution network based on sliding mode control according to claim 1 or 2, characterized in that: The linear extended state observer of S2 is designed as follows, The linear extended state observer is defined as follows: Among them, z1 is the actual trajectory q of the N-joint live working intelligent device φ (t), z2 is the observed value of F(t) for uncertain terms and unknown disturbances in the dynamic model of the N-joint live-line working intelligent equipment, e1=z1(t)-q φ (t) is the observation error of the linear extended state observer to the actual output trajectory.

4. A method for controlling intelligent equipment for live working in a distribution network based on sliding mode control according to claim 1 or 2, characterized in that: The global non-singular terminal sliding surface of S3 is designed as follows: The global non-singular terminal sliding surface is designed as: Among them, ηe(t) is the tracking error proportional term of the N-joint live-working intelligent device, and η is the proportional term parameter adjustment gain; is a non-singular term, ω, and σ are non-singular parameter adjustment gains, which must satisfy: and σ is a positive odd number; The first-order differential of the global non-singular terminal sliding surface is as follows: in, is the first-order differential of s(t) with respect to time t, They are s1(t), s2(t), …, S N (t), S N+1 (t), S N+2 (t)The first-order differential with respect to time t.

5. A method for controlling intelligent equipment for live working in a distribution network based on sliding mode control according to claim 1 or 2, characterized in that: The S4 neural network adaptive constant speed approach rate is designed as follows: The adaptive constant speed approach rate is designed as follows: in, is the adaptive term parameter of the constant velocity approach rate, 6. The method for controlling intelligent equipment for live working in distribution network based on sliding mode control according to claim 5 is characterized in that: The S4 also includes, The neural network adaptation rate is designed as: ζ=[ζ1(t),ζ2(t),...,ζ N (t),ζ N+1 (t),ζ N+2 (t)] T in, is the constant approach rate adaptive term parameter is the approximate value of , ζ is the control gain of the adaptive rate, h(x) is the hidden layer activation function of the neural network observer, is the optimal weight of the neural network from the hidden layer to the output layer, and Γ is between and The approximate error of It is W * The estimated value of yes Adaptation rate; The hidden layer activation function is chosen as the cubic B-spline basis function, which is defined as: h(x)=[h1(t),h2(t),…,h N (t),h N+1 (t),h N+2 (t)] When || xo i ||≤h i When i=1,2…,N+2 When h i <||xo i ||≤2h i When i=1,2…,N+2 When 2h i <||xo i ||, and i=1,2…,N+2 h i (x)=0 Among them, ||xo i || is the distance between the input vector and the center vector in Euclidean form; x is the input vector; o and o i is the center vector; h i is the width of the cubic B-spline function.

7. A method for controlling intelligent equipment for live working in a distribution network based on sliding mode control according to claim 1 or 2, characterized in that: The controller design of the S5 is as follows: Combining the linear extended state observer, the global non-singular terminal sliding mode surface and the neural network adaptive constant velocity approach rate, the neural network adaptive global non-singular terminal sliding mode controller of the N-joint live working intelligent equipment system based on the linear extended state observer is designed as follows:

Images