A path planning method for a mechanical arm of a well repair equipment

Abstract

The present invention belongs to the technical field of automatic control of well repair equipment, and in particular, relates to a method for path planning of a mechanical arm of well repair equipment. A method for path planning of a mechanical arm of well repair equipment takes path energy consumption as the objective function and the position coordinates of the end position of the mechanical arm as the decision variable, constructs a mathematical model for path planning of the mechanical arm of a two-layer platform complete pipe arrangement system, and adopts a particle swarm algorithm to solve it, so as to realize the minimum energy consumption path planning of the joint space of the mechanical arm of the ground, the drilling table and the two-layer platform complete system. The method for path planning of the mechanical arm of the well repair equipment includes the steps of establishing a three-dimensional spatial model of the complete pipe arrangement system; establishing a kinematic model of the mechanical arm of the two-layer platform complete pipe arrangement system; constructing a mathematical model for path planning of the mechanical arm of the two-layer platform complete pipe arrangement system; using a radial basis function neural network for system identification, and establishing a mathematical model with the joint angular position and angular velocity of the mechanical arm as input and the path tracking energy consumption of the mechanical arm as output.

Description

Technical Field

[0001] The invention belongs to the technical field of automatic control of well repair equipment, and in particular relates to a path planning method for a mechanical arm of well repair equipment. Background Art

[0002] As an important equipment in the well repair process, the second-level platform automatic pipe removal and arrangement system refers to an automated control device that automatically removes and arranges pipes on the second-level platform by remotely operating the mechanical arm on the second-level platform of the drilling rig from the drilling platform. According to specific process requirements, the second-level platform automatic pipe removal and arrangement system needs to complete the movement form and power requirements required for a series of functions such as moving, tilting, and straightening to the second-level platform, and determine the pipe string processing process (procedure) based on the principles of safety and efficiency.

[0003] As can be seen from the above, the robot arm plays an important role in the automatic pipe removal and drainage system, and it is the key to implement and complete automated operations. In order to achieve safe and efficient operation of the intelligent pipe drainage system of the ground, drilling table and second-floor platform, based on different parameters such as pipe column geometry and mass, the working parameters such as the path, operating speed and maximum lifting mass of the pipe column handling equipment are determined, the working parameters such as the clamping force of the pipe drainage manipulator are determined, the pipe column discharge strategy and automatic locking method are determined, and finally the robot arm path planning and tracking control are carried out with the goal of reducing the energy consumption of the pipe drainage system, which has become the key to improving the safety and efficiency of the above-mentioned pipe drainage system. Summary of the invention

[0004] The present invention provides a method for well repair equipment robot arm path planning. The method takes path energy consumption as the objective function, takes the position coordinates of the end of the robot arm as the decision variable, considers the actual working conditions to establish the constraint conditions of the optimization problem, constructs a mathematical model for the path planning of the robot arm of the two-layer platform whole machine pipe arrangement system, and adopts a particle swarm algorithm to solve it, so as to realize the minimum energy consumption path planning of the joint space of the robot arm of the ground, the drilling table and the two-layer platform whole machine system.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] A method for path planning of a mechanical arm of well repair equipment comprises the following steps:

[0007] Step 1: Based on the space where the whole machine pipe system is located on the ground, the drilling table and the second floor, a three-dimensional space model of the whole machine pipe system is established;

[0008] Step 2: Establish the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system;

[0009] Step 3: Taking the path energy consumption as the objective function, the position coordinates of the end position of the robot arm as the decision variable, and the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system described in step 2 as the constraint condition, a mathematical model of the path planning of the robot arm of the two-layer platform whole machine pipe arrangement system is constructed;

[0010] Step 4: Use radial basis function neural network to identify the system, establish a mathematical model with the robot arm joint angular position and angular velocity as input and the robot arm path tracking energy consumption as output, and use it as the objective function of energy consumption optimization.

[0011] Further preferably, it also includes:

[0012] Step 5: Fuzzify the controller input and output in the neural network used in step 4.

[0013] Preferably, step 5 can be specifically described as:

[0014] Formulate control strategies based on fuzzy decision tables;

[0015] The weighted average method is used to defuzzify the fuzzy controller variables and obtain the controller output variables.

[0016] Preferably, step 1 can be specifically described as: using the grid method, the space where the ground, drilling table and the second-floor platform where the whole machine pipe system is located is divided into equal-sized square units to establish a three-dimensional space model of the whole machine pipe system.

[0017] Preferably, step 2 can be specifically described as: using the DH method to establish a kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system.

[0018] Preferably, the mathematical model of the robot arm path planning of the two-layer platform whole machine pipe arrangement system constructed in step 3 can be specifically described as:

[0019] Formula (1);

[0020] In formula (1), Plan the length of the robot path, is the end coordinate of the robot arm, is the minimum value of the end coordinate of the robot arm in the environment model, is the maximum value of the end coordinate of the robot arm in the environment model.

[0021] Preferably, the energy consumption optimization objective function constructed in step 4 can be specifically described as:

[0022] Formula (3);

[0023] In formula (3), is the energy consumption of the robot path tracking, is a matrix, representing the pitch angle, roll angle, and yaw angle values ​​of the robot arm joint; is a matrix, representing the pitch angular velocity, roll angular velocity, and yaw angular velocity values ​​of the robot joint; is the minimum value that the robot arm joint can reach; is the maximum value that the robot arm joint can reach.

[0024] Preferably, a particle swarm algorithm is used to solve the mathematical model of the robot path planning of the two-layer whole machine pipe arrangement system constructed in step 3 and the energy consumption optimization objective function constructed in step 4;

[0025] Among them, the particle swarm algorithm updates the position parameters to meet the following requirements:

[0026] Formula (2);

[0027] In formula (2), , ; is the inertia factor; is the acceleration constant; is a random number in [0,1]; is the speed weight coefficient; is the flying speed of particle i; is the position of particle i.

[0028] The present invention provides a method for path planning of a mechanical arm of a well repair equipment, which includes the steps of establishing a three-dimensional spatial model of a whole pipe arrangement system; establishing a kinematic model of a mechanical arm of a two-layer platform whole pipe arrangement system; constructing a mathematical model for path planning of a mechanical arm of a two-layer platform whole pipe arrangement system; using a radial basis function neural network to identify the system, and establishing a mathematical model with the mechanical arm joint angular position and angular velocity as input and the mechanical arm path tracking energy consumption as output. A method for path planning of a mechanical arm of a well repair equipment having the above-mentioned steps is characterized by analyzing the motion form and power requirements required by a well repair pipe string processing system to complete a series of functions such as moving, tilting, and straightening to a two-layer platform, and determining a pipe string processing program based on the principle of safety and efficiency; taking the path energy consumption as the objective function, taking the mechanical arm end position coordinates as the decision variable, considering the actual working conditions to establish the constraints of the optimization problem, constructing a mathematical model for path planning of a mechanical arm of a two-layer platform whole pipe arrangement system, and using a particle swarm algorithm to solve it, so as to realize the minimum energy consumption path planning of the joint space of the mechanical arm of the ground, the drilling table, and the two-layer platform whole system. DETAILED DESCRIPTION

[0029] The present invention provides a method for well repair equipment robot arm path planning. The method takes path energy consumption as the objective function, takes the position coordinates of the end of the robot arm as the decision variable, considers the actual working conditions to establish the constraint conditions of the optimization problem, constructs a mathematical model for the path planning of the robot arm of the two-layer platform whole machine pipe arrangement system, and adopts a particle swarm algorithm to solve it, so as to realize the minimum energy consumption path planning of the joint space of the robot arm of the ground, the drilling table and the two-layer platform whole machine system.

[0030] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Embodiment 1

[0031] A method for path planning of a mechanical arm of well repair equipment comprises the following steps:

[0032] Step 1: Based on the space where the whole machine pipe system is located on the ground, the drilling table and the second floor, a three-dimensional space model of the whole machine pipe system is established;

[0033] Step 2: Establish the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system;

[0034] Step 3: Taking the path energy consumption as the objective function, the position coordinates of the end position of the robot arm as the decision variable, and the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system described in step 2 as the constraint condition, a mathematical model of the path planning of the robot arm of the two-layer platform whole machine pipe arrangement system is constructed;

[0035] Step 4: Use radial basis function neural network to identify the system, establish a mathematical model with the robot arm joint angular position and angular velocity as input and the robot arm path tracking energy consumption as output, and use it as the objective function of energy consumption optimization.

[0036] And, as a more preferred embodiment of the present invention, step 5: fuzzy processing is performed on the controller input and output in the neural network used in step 4.

[0037] The following embodiments are further taken as examples to explain in detail the specific features of step 2 to step 5, and the present invention is illustrated based on the features of each specific step. Embodiment 2

[0038] Specifically, the second embodiment includes all the technical features of the first embodiment. In addition, the features of step 1 are further explained as follows in the second embodiment.

[0039] Specifically, step 1 can be described as follows: using the grid method, the space where the ground, drilling table and the second-floor platform's entire pipe system are located is divided into equal-sized square units to establish a three-dimensional space model of the entire pipe system.

[0040] It is worth noting that the grid method, as an environmental modeling method, is essentially to divide the working three-dimensional space into units and represent it with equal-sized blocks. Therefore, the grid size is an important factor affecting the performance of the planning algorithm. The smaller the grid, the more detailed and accurate the three-dimensional space model established, but the amount of calculation is large and the time is long; on the contrary, the smaller the grid, the rougher the model established, the lower the accuracy, the less calculation, and the time is short. Embodiment 3

[0041] Specifically, the third embodiment includes all the technical features of the first embodiment. In addition, the features of step 2 are further explained in the third embodiment as follows.

[0042] Among them, step 2 can be specifically described as: using the DH method to establish the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system. Embodiment 4

[0043] Specifically, the fourth embodiment includes all the technical features of the first embodiment. In addition, the features of step 3 are further explained as follows in the fourth embodiment.

[0044] Among them, the mathematical model of the robot arm path planning of the two-layer platform whole machine pipe arrangement system constructed in step 3 can be specifically described as:

[0045] Formula (1);

[0046] In formula (1), Plan the length of the robot path, is the end coordinate of the robot arm, is the minimum value of the end coordinate of the robot arm in the environment model, is the maximum value of the end coordinate of the robot arm in the environment model.

[0047] It is worth noting that the above strategy is adopted because, generally speaking, it is understandable to those skilled in the art that the shorter the path, the less energy the robot consumes. Therefore, the path length is used as the objective function, the position coordinates of the end of the robot are used as the decision variable, and the constraints of the above optimization problem are established in combination with the actual working conditions. Embodiment 5

[0048] Specifically, the fifth embodiment includes all the technical features of the first embodiment. In addition, the features of step 4 are further explained as follows in the fifth embodiment.

[0049] Specifically, the energy consumption optimization objective function constructed in step 4 can be specifically described as:

[0050] Formula (3);

[0051] In formula (3), is the energy consumption of the robot path tracking, is a matrix, representing the pitch angle, roll angle, and yaw angle values ​​of the robot arm joint; is a matrix, representing the pitch angular velocity, roll angular velocity, and yaw angular velocity values ​​of the robot joint; is the minimum value that the robot arm joint can reach; is the maximum value that the robot arm joint can reach.

[0052] It should be noted that, on the basis of completing the path planning of the above-mentioned embodiment, the radial basis function (RBF) neural network is further used to realize the path tracking problem of the robot arm based on energy consumption. Specifically, a mathematical model with the angular position and angular velocity of the robot arm joints as input and power consumption as output is established, and it is used as the objective function of energy consumption optimization. The boundary conditions of each joint of the robot arm are used as constraints, and the angular position and angular velocity are used as decision variables.

[0053] The radial basis neural network (RBF) used is a feedforward neural network with the best approximation and global optimal performance. It has the advantages of simple structure, strong adaptive learning ability and fast convergence speed. It includes an input layer, a hidden layer and an output layer.

[0054] The first layer of RBF is an input layer composed of neurons responsible for receiving multiple data sources of the robot arm joint angular position and angular velocity. The joint position and angular velocity data signals enter the neural network through the input layer, and the data corresponds to each node of the neural network one by one.

[0055] The second layer of the RBF neural network is the hidden layer, which mainly completes the nonlinear transformation of the input robot data and transmits the transformed data information to the next layer of neurons. The number of hidden layer nodes depends on the robot data. Generally, the more nodes there are, the higher the prediction accuracy of the model, but too many nodes can easily cause overfitting. The Gaussian function is selected as the radial basis function to respond to the input signal.

[0056] The third layer of the RBF neural network is the output layer. The relationship between the hidden layer and the output layer is expressed as ,When RBF neural network is used for the energy consumption prediction of the ,robot arm, the network continuously adjusts the connection weights between the ,hidden layer and the output layer, and performs weighted summation on the output ,values ​​of the hidden layer to obtain the energy consumption prediction value ,at the next moment. Embodiment 6

[0057] Specifically, the sixth embodiment includes all the technical features of the first embodiment. In addition, the features of step 5 are further explained as follows in the sixth embodiment.

[0058] Specifically, step 5 can be described as follows:

[0059] Formulate control strategies based on fuzzy decision tables;

[0060] The weighted average method is used to defuzzify the fuzzy controller variables and obtain the controller output variables.

[0061] It should be noted that fuzzy control is an intelligent control method that imitates human fuzzy reasoning and makes decisions. It is based on fuzzy set theory, fuzzy logic reasoning and fuzzy language, and mainly includes four aspects: variable fuzzification, fuzzy rule formulation, fuzzy reasoning and defuzzification. In the embodiment of the present invention, the goal is to minimize the difference between the tracking path and the planned path, the error and error change rate are the input of the fuzzy controller, the motor power and the joint angle of the mechanical arm are the controller output, and the triangular membership function is used to fuzzify the controller input and output. The specific steps can be referred to as follows: by using negative large, negative medium, negative small, zero, positive small, positive medium, and positive large as input and output states, a fuzzy rule matrix table is established. According to the input data change, the control strategy is formulated according to the decision table, and the weighted average method is used to defuzzify the fuzzy controller variables to obtain the final controller output variables, and finally realize the path tracking of the mechanical arm to the pipe column placement. Embodiment 7

[0062] Specifically, the seventh embodiment includes all the technical features of the first embodiment. In addition, the seventh embodiment further explains the following process of constructing a mathematical model for the robot path planning of the two-layer platform whole machine pipe arrangement system in step 3 and the solution process of the energy consumption optimization objective function in step 4.

[0063] Specifically, the particle swarm algorithm updates the position parameters to meet the following conditions:

[0064] Formula (2);

[0065] In formula (2), , ; is the inertia factor; is the acceleration constant; is a random number in [0,1]; is the speed weight coefficient; is the flying speed of particle i; is the position of particle i.

[0066] Of course, the above solution process is only an example, and those skilled in the art can perform secondary processing optimization on the solution process according to actual working conditions.

[0067] So far, based on the steps of a well repair equipment manipulator path planning method provided by the present invention, a mathematical model for the manipulator path planning of the two-layer platform whole machine pipe laying system has been completed, and the particle swarm algorithm has been used to solve it.

[0068] The present invention provides a method for path planning of a mechanical arm of a well repair equipment, which includes the steps of establishing a three-dimensional spatial model of a whole pipe arrangement system; establishing a kinematic model of a mechanical arm of a two-layer platform whole pipe arrangement system; constructing a mathematical model for path planning of a mechanical arm of a two-layer platform whole pipe arrangement system; using a radial basis function neural network to identify the system, and establishing a mathematical model with the mechanical arm joint angular position and angular velocity as input and the mechanical arm path tracking energy consumption as output. A method for path planning of a mechanical arm of a well repair equipment having the above-mentioned steps is characterized by analyzing the motion form and power requirements required by a well repair pipe string processing system to complete a series of functions such as moving, tilting, and straightening to a two-layer platform, and determining a pipe string processing program based on the principle of safety and efficiency; taking the path energy consumption as the objective function, taking the mechanical arm end position coordinates as the decision variable, considering the actual working conditions to establish the constraints of the optimization problem, constructing a mathematical model for path planning of a mechanical arm of a two-layer platform whole pipe arrangement system, and using a particle swarm algorithm to solve it, so as to realize the minimum energy consumption path planning of the joint space of the mechanical arm of the ground, the drilling table, and the two-layer platform whole system.

[0069] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A path planning method for a well repair equipment mechanical arm, characterized in that: The steps include: Step 1: Based on the space where the whole machine pipe system is located on the ground, the drilling table and the second floor, a three-dimensional space model of the whole machine pipe system is established; Step 2: Establish the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system; Step 3: Taking the path energy consumption as the objective function, the position coordinates of the end position of the robot arm as the decision variable, and the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system described in step 2 as the constraint condition, a mathematical model of the path planning of the robot arm of the two-layer platform whole machine pipe arrangement system is constructed; Step 4: Use radial basis function neural network to identify the system, establish a mathematical model with the robot joint angular position and angular velocity as input and the robot path tracking energy consumption as output, and use it as the objective function of energy consumption optimization; The mathematical model of the robot arm path planning of the two-layer whole machine pipe arrangement system constructed in step 3 is specifically described as follows: Formula (1); In formula (1), Plan the length of the robot path, is the end coordinate of the robot arm, is the minimum value of the end coordinate of the robot arm in the environment model, is the maximum value of the end coordinate of the robot arm in the environment model; The objective function of energy consumption optimization constructed in step 4 is specifically described as: Formula (3); In formula (3), is the energy consumption of the robot path tracking, is a matrix, representing the pitch angle, roll angle, and yaw angle values ​​of the robot arm joint; is a matrix, representing the pitch angular velocity, roll angular velocity, and yaw angular velocity values ​​of the robot joint; is the minimum value that the robot arm joint can reach; is the maximum value that the robot arm joint can reach; The particle swarm algorithm is used to solve the mathematical model of the robot path planning of the two-layer whole machine pipe arrangement system constructed in step 3 and the objective function of energy consumption optimization constructed in step 4. Among them, the particle swarm algorithm updates the position parameters to meet the following requirements: Formula (2); In formula (2), , ; is the inertia factor; is the acceleration constant; is a random number in [0,1]; is the speed weight coefficient; is the flying speed of particle i; is the position of particle i.

2. A method for well repair equipment mechanical arm path planning according to claim 1, characterized in that: Also included are: Step 5: Fuzzify the controller input and output in the neural network used in step 4.

3. A method for well repair equipment mechanical arm path planning according to claim 2, characterized in that: Step 5 is specifically described as follows: Formulate control strategies based on fuzzy decision tables; The weighted average method is used to defuzzify the fuzzy controller variables and obtain the controller output variables.

4. A method for well repair equipment robot arm path planning according to claim 1, characterized in that: Step 1 is specifically described as follows: using the grid method, the space where the ground, drilling table and the second-floor platform's entire pipe system are located is divided into equal-sized square units to establish a three-dimensional space model of the entire pipe system.

5. A method for well repair equipment mechanical arm path planning according to claim 1, characterized in that: The specific description of step 2 is: Use the DH method to establish the kinematic model of the robot arm of the two-layer platform whole machine pipe arrangement system.

Images