A variable working condition control method and system for an underwater robot for aquaculture

Abstract

The invention discloses a variable working condition operation control method and system for an underwater robot for aquaculture. The method comprises the following steps: taking a number of control input increments of the underwater robot as optimization targets, setting control weights of a number of optimization targets based on state parameters of the underwater robot, and constructing a weight adjustment rule table according to the mapping relationship between the state parameters and the control weights; collecting the state parameters of the underwater robot, searching the control weights corresponding to the state parameters in the weight adjustment rule table, constructing an optimization objective function, calculating the minimum value of the optimization objective function, obtaining the optimal control input increment of the underwater robot, applying the control input at the current moment to the underwater robot, and driving the underwater robot to perform a control task; updating the state parameters of the underwater robot in real time, and repeatedly performing the above until the underwater robot completes the predetermined control task.

Description

Technical Field

[0001] The present invention relates to the field of aquaculture equipment research and development, and in particular to a variable working condition operation control method and system of an aquaculture underwater robot. Background Art

[0002] As an important economic pillar industry, aquaculture plays an important role in ensuring food supply. With the rapid development of the aquaculture industry in recent years, its contribution to the economy has become increasingly significant. However, the industry is facing problems such as insufficient automation, aging labor force structure and environmental pollution, which urgently need to be solved through technological innovation.

[0003] At present, underwater robots have been used in the field of aquaculture to perform tasks such as target recognition and product capture. These robots are designed to adapt to complex underwater environments and dynamically changing operating targets. Domestic and foreign researchers have made progress in the research and application of underwater robots and developed a variety of control methods, which have improved the efficiency and effectiveness of underwater operations to a certain extent.

[0004] In aquaculture operations, the precise tracking and control capabilities of underwater robots are crucial, but achieving this goal is still challenging. Existing control methods for underwater robots still have limitations in the face of changing operating environments and complex tasks. For example, in fast-moving target capture operations, the robot needs to be able to respond quickly and accurately, while in delicate shellfish or sea cucumber picking operations, more sophisticated and stable posture control is required. These needs put higher demands on robot control systems, showing the shortcomings of existing technologies in terms of adaptability, accuracy and stability. Therefore, there is an urgent need to develop an intelligent control system to improve the operating capabilities and efficiency of underwater robots under various working conditions. Summary of the invention

[0005] The present invention proposes a variable working condition operation control method and system for an aquaculture underwater robot, which solves the problems of poor adaptability, accuracy and stability of existing underwater robots when completing tasks under various working conditions.

[0006] In order to solve the above technical problems, the present invention provides a variable working condition operation control method of an aquaculture underwater robot, comprising the following steps:

[0007] Step S1: taking several control input increments of the underwater robot as optimization targets, setting control weights of several optimization targets based on state parameters of the underwater robot, and constructing a weight adjustment rule table according to the mapping relationship between the state parameters and the control weights, wherein the state parameters include speed, depth from the seabed, and task type;

[0008] Step S2: collecting the state parameters of the underwater robot, searching the control weights corresponding to the state parameters in the weight adjustment rule table, constructing an optimization objective function, calculating the minimum value of the optimization objective function, obtaining the optimal control input increment of the underwater robot, applying the control input at the current moment to the underwater robot, and driving the underwater robot to perform the control task;

[0009] Step S3: updating the state parameters of the underwater robot in real time;

[0010] Step S4: Repeat steps S2 to S3 until the underwater robot completes the predetermined control task.

[0011] Preferably, constructing a weight adjustment rule table according to the mapping relationship between state parameters and control weights in step S1 includes the following steps: taking the speed, depth from the seabed and task type of the underwater robot as input, taking the weight of the optimization target as output, listing all combinations of speed, depth from the seabed and task type, setting the control weight for each combination, and obtaining a weight adjustment rule table.

[0012] Preferably, setting the control weight of each combination comprises the following steps:

[0013] Step S11: define the fuzzy sets of each fuzzy variable, the input fuzzy variables include speed, depth from the seabed and task type, the output fuzzy variable is weight, the fuzzy set of speed is low speed SLOW and high speed FAST, the fuzzy set of depth from the seabed is low S, medium M, high L, the fuzzy set of task type is 0, 1, 2, 3, where the diving stage is defined as 0, the search operation stage is defined as 1, the precision operation stage is defined as 2, and the return stage is defined as 3, and the fuzzy sets of each weight are: small, medium, and large;

[0014] Step S12: creating a membership function for each fuzzy variable, converting the actual value of the fuzzy variable into the membership value of the fuzzy set;

[0015] Step S13: Setting fuzzy rules to map the fuzzy set of input fuzzy variables to the fuzzy set of output fuzzy variables.

[0016] Preferably, the membership function of the speed u in step S12 is set as:

[0017]

[0018] The membership function of the depth d from the seabed is set as:

[0019]

[0020]

[0021] The membership function of task type T is set as:

[0022]

[0023] Among them, NB is negative and large; NS is negative and small; PS is positive and small; PB is positive and large.

[0024] Preferably, the optimization objective function in step S2 includes an energy consumption control cost function, a trajectory tracking cost function and a posture control cost function, and the expression of the optimization objective function is:

[0025] J O (k) = J E (k)·w E (k)+J P (k)·w P (k)+J A (k)·w A (k);

[0026] In the formula, J E (k) is the energy consumption control cost function; J P (k) is the trajectory tracking cost function; J A (k) is the posture control cost function; w E (k), w P (k) and w A (k) are J E (k), J P (k), J A The weight of (k).

[0027] Preferably, the energy consumption control cost function J E The expression of (k) is:

[0028]

[0029] Where Nc is the control time domain; k E is the weight coefficient; u() is the increment of control input; u max and u min Represent the upper and lower limits of the control input respectively.

[0030] Preferably, the trajectory tracking cost function J P The expression of (k) is:

[0031]

[0032] In the formula, Q is the weight coefficient matrix; Np is the prediction time domain; w D is the gain coefficient of the vertical error; s(k+i|k) is the predicted path coordinate; s d(k+i|k) is the reference path coordinate; x(k+i|k), y(k+i|k), z(k+i|k) represent the x, y, and z axis coordinates of the predicted path respectively; x d (k+i), y d (k+i), z d (k+i) represents the x, y, and z axis coordinates of the reference path respectively; z max and z min They represent the upper and lower limits of the z-axis direction respectively.

[0033] Preferably, the posture control cost function J A The expression of (k) is:

[0034]

[0035] In the above formula, φ(k+i|k) represents the roll angle at time k+i predicted at time k; P1 and P2 are weights; Np is the prediction time domain; is the slack variable; φ max ,φ min ,θ max ,θ min The upper and lower limits of the soft constraints for roll and pitch attitude; are the upper and lower limits of the hard constraints of the roll and pitch attitudes; λ is a binary switch signal; It is the logical inversion of λ. When λ=1, When λ=0,

[0036] Preferably, calculating the minimum value of the optimization objective function by a Casadi solver in step S3 comprises the following steps:

[0037] Step S31: configure the Casadi solver, set the target optimization function as the objective function, the constraint of the energy consumption control cost function as the input constraint, the constraints of the trajectory tracking cost function and the attitude control cost function as the state constraint, and set the solution method to the interior point method;

[0038] Step S32: Call the Casadi solver to execute the optimization solution process until the set maximum number of iterations is reached.

[0039] The present invention also provides a variable working condition operation control system for an aquaculture underwater robot, which is implemented based on the variable working condition operation control method of an aquaculture underwater robot, and includes a detection and perception module, an optimization control module and a decision switching module;

[0040] The detection and perception module includes a target detection module and a motion perception module. The target detection module is used to detect the aquaculture operation target and the environmental information of the underwater robot; the motion perception module is used to perceive the real-time position and posture of the underwater robot;

[0041] The optimization control module includes an energy consumption control module, a trajectory tracking control module and a posture control module. The energy consumption control module is used to construct an energy consumption control target model during the operation of the underwater robot; the trajectory tracking control module is used to construct a trajectory tracking control target model during the operation of the underwater robot; the posture control module is used to construct a posture control target model during the operation of the underwater robot;

[0042] The decision switching module designs an adaptive fuzzy task switching decision according to the control task of the underwater robot and the real-time state of the underwater robot obtained by the detection and perception module, and performs online adaptive adjustment on the weight of the optimization objective function.

[0043] The beneficial effects of the present invention include at least:

[0044] 1. The control input increment of the underwater robot is used as the optimization target to achieve precise adjustment of the robot's motion. Through continuous incremental adjustment, the robot is gradually guided to reach the optimal working state, which can more flexibly respond to real-time changing operating conditions and environmental disturbances;

[0045] 2. According to the real-time status information of the underwater robot, such as position, posture and speed, the weight of the optimization target is dynamically updated. By adjusting the rule table, the importance of different optimization targets can be automatically adjusted according to the current operation mode and environmental conditions, providing a control strategy with high adaptability, fast response speed and high precision. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present invention;

[0047] Figure 2 It is a task type membership function diagram of an embodiment of the present invention;

[0048] Figure 3 It is a speed membership function diagram of an embodiment of the present invention;

[0049] Figure 4 It is a speed membership function diagram of an embodiment of the present invention;

[0050] Figure 5 A schematic diagram of the system structure of an embodiment of the present invention;

[0051] Figure 6 Schematic diagram of the navigation trajectory of the underwater robot in an embodiment of the present invention;

[0052] Figure 7 Schematic diagram of the three-axis tracking error of the underwater robot in an embodiment of the present invention;

[0053] Figure 8 Schematic diagram of energy consumption of an underwater robot at each stage in an embodiment of the present invention;

[0054] Fig. 9 Schematic diagram of the roll angle change of the underwater robot in an embodiment of the present invention;

[0055] Fig.10 Schematic diagram of the change of the longitudinal inclination angle of the underwater robot in an embodiment of the present invention;

[0056] Fig.11 A schematic diagram of output changes of a task switching decision maker in an embodiment of the present invention; DETAILED DESCRIPTION

[0057] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0058] like Figure 1 As shown, an embodiment of the present invention provides a variable working condition operation control method of an aquaculture underwater robot, comprising the following steps:

[0059] Step S1: taking several control input increments of the underwater robot as optimization targets, setting control weights of several optimization targets based on the state parameters of the underwater robot, and constructing a weight adjustment rule table according to the mapping relationship between the state parameters and the control weights. The state parameters include speed, depth from the seabed and mission type.

[0060] The control input of the underwater robot for aquaculture is the force / torque of six degrees of freedom, and the increment of the force / torque of six degrees of freedom is used as the optimization target. In order to realize the adaptive switching of the underwater robot for aquaculture between different operation modes, it is necessary to design a decision rule based on fuzzy logic. According to the real-time status and operation task of the underwater robot, the weight of the optimization objective function is adjusted online and adaptively.

[0061] Specifically, the speed, depth from the seabed and task type of the underwater robot are taken as input, the weight of the optimization target is taken as output, all combinations of speed, depth from the seabed and task type are listed, the control weight of each combination is set, and the weight adjustment rule table is obtained, including the following steps:

[0062] Step S11: define the fuzzy sets of each fuzzy variable, the input fuzzy variables include speed, depth from the seabed and mission type, the output fuzzy variables are weights, the fuzzy set of speed is low speed SLOW and high speed FAST, the fuzzy set of depth from the seabed is low S, medium M, high L, the mission type includes diving stage, search operation stage, precision operation stage and return stage, the fuzzy sets are 0, 1, 2, 3, among which the diving stage is defined as 0, the search operation stage is defined as 1, the precision operation stage is defined as 2, and the return stage is defined as 3, and the fuzzy sets of each weight are: small, medium, and large.

[0063] Step S12: Figures 2 to 4 As shown, a membership function is created for each fuzzy variable to convert the actual value of the fuzzy variable into the membership value of the fuzzy set; Figure 2 It can be seen that when the mission type is 0, NB is 1, NS, PS, PB are 0; the speed can be Figure 3 The membership function diagram corresponds to the low speed membership (SLOW) which decreases linearly in the speed range of 0m / s-3m / s. When the speed is greater than 3m / s, the SLOW membership is 0 and the FAST membership is 1. Figure 4 It can be seen that when the underwater robot is 0m from the seabed, the S membership is 1, and the M and L memberships are 0.

[0064] The membership function of the speed u is:

[0065]

[0066] The membership function of the depth d from the seafloor is:

[0067]

[0068] The membership function of task type T is:

[0069]

[0070]

[0071] Among them, NB is negative and large; NS is negative and small; PS is positive and small; PB is positive and large.

[0072] Step S13: According to experience or expert knowledge, fuzzy rules are set to map the fuzzy set of input fuzzy variables to the fuzzy set of output fuzzy variables. The fuzzy weight adjustment rules finally obtained are shown in Table 1.

[0073] Table 1 Fuzzy weight adjustment rules

[0074]

[0075] At the same time, the defuzzification rules are set. After obtaining the fuzzy output of each weight, the centroid method is used to defuzzify the output to output the exact value of the weight.

[0076] The fuzzy output includes the weight w of the energy consumption control cost function E , trajectory tracking cost function w P , posture control cost function w A and vertical error weight w D , the output quantity adopts the triangular membership function, where w E The domain of w is [0,50], P The domain of w is [1,10], D The domain of w is [0,3], A The domain is [0,30], and their states are {S,M,L}, i.e. {small, medium, large}.

[0077] Step S2: Collect the state parameters of the underwater robot, search the control weights corresponding to the state parameters in the weight adjustment rule table, construct the optimization objective function, calculate the minimum value of the optimization objective function, obtain the optimal control input increment of the underwater robot, apply the control input at the current moment to the underwater robot, and drive the underwater robot to perform the control task.

[0078] Specifically, the optimization objective function includes the energy consumption control cost function, the trajectory tracking cost function and the attitude control cost function. The expression of the optimization objective function is:

[0079] J O (k) = J E (k)·w E (k)+J P (k)·w P (k)+J A (k)·w A (k);

[0080] In the formula, J E (k) is the energy consumption control cost function; J P (k) is the trajectory tracking cost function; J A (k) is the posture control cost function; w E (k), w P (k) and w A (k) are J E (k), J P (k), J A The weight of (k).

[0081] Energy consumption control cost function J E The expression of (k) is:

[0082]

[0083] Where Nc is the control time domain; k E is the initial weight coefficient of the energy consumption control cost function. Since energy consumption is related to input increment, but the degree of correlation is related to the specific type of underwater robot, the energy consumption module can be at the same order of magnitude as other modules by adjusting the initial weight coefficient, thereby enhancing the versatility of the task switching decision maker. This value is mainly used to adjust the order of magnitude, so it can be taken as 10. n (n=-2, -1, 0, 1, 2..), according to debugging experience, this embodiment takes n=2; u() is the increment of control input; u max and u min Represent the upper and lower limits of the control input respectively.

[0084] Trajectory tracking cost function J P The expression of (k) is:

[0085]

[0086] In the formula, Q is a weight coefficient matrix, which is used to adjust the weights of the three-axis coordinates in the cost function. According to the actual test results, the weights of the directions with poor tracking effects can be appropriately increased. According to the debugging experience, this embodiment takes a three-row and three-column diagonal matrix with all elements set to 1; Np is the prediction time domain; w D is the gain coefficient of the vertical error; s(k+i|k) is the predicted path coordinate; s d (k+i|k) is the reference path coordinate, x(k+i|k), y(k+i|k), z(k+i|k) represent the x, y, and z axis coordinates of the predicted path respectively; d (k+i), y d (k+i), z d (k+i) represents the x, y, and z axis coordinates of the reference path respectively; z max and z min They represent the upper and lower limits of the z-axis direction respectively.

[0087] Posture control cost function J A The expression of (k) is:

[0088]

[0089] In the above formula, φ(k+i|k) represents the roll angle at the k+i moment predicted at the kth moment; P1 and P2 are weights. The goal is to make the aquaculture underwater robot meet the posture requirements while effectively tracking the trajectory. Therefore, the debugging experience is to increase from 0 and stop when the path tracking effect is seriously affected. A more appropriate value is selected from the interval. In this embodiment, the values ​​are P1=0.002, P2=1, and P3=1; Np is the prediction time domain; is the slack variable; φ max ,φ min ,θ max ,θ min The upper and lower limits of the soft constraints for roll and pitch attitude; are the upper and lower limits of the hard constraints of the roll and pitch attitudes; λ is a binary switch signal; It is the logical inversion of λ. For example, when λ=1, When λ=0,

[0090] After obtaining the optimization objective function, the minimum value of the optimization objective function is solved by iterative calculation using the Casadi solver, including the following steps:

[0091] Step S21: configure the Casadi solver, set the target optimization function as the objective function, the constraint of the energy consumption control cost function as the input constraint, the constraints of the trajectory tracking cost function and the attitude control cost function as the state constraint, and set the solution method to the interior point method;

[0092] Step S22: Call the Casadi solver to execute the optimization process until the optimization goal is met or the maximum number of iterative calculations is reached. Set the upper limit of the number of iterations max_iter = 1000 and the threshold value of the objective function value tol = 1e-6.

[0093] By setting the force / torque increments of the six degrees of freedom as unknowns to construct the target optimization function and optimizing and solving it, the optimal control input increments in a certain time domain in the future can be solved, and the first set of solutions can be used for current control. The current control input of the underwater robot is the control input of the previous moment plus the increment of the control input calculated at the current moment. The solution of the remaining time domain is used as the initial value of the optimization solution at the next moment, and rolling optimization is performed to achieve tracking error convergence.

[0094] Step S3: Update the state parameters of the underwater robot in real time, and repeat the above steps until the underwater robot completes the predetermined control task.

[0095] The method of the present invention can be used for the "diving-searching-precision operation-recovery" scenario in typical aquaculture operations. The designed variable operating condition switching decision and multi-objective variable constraint optimization control method can meet the needs of aquaculture operations in complex environments.

[0096] like Figure 5 As shown, an embodiment of the present invention further provides a variable operating condition control system for an aquaculture underwater robot, including a detection and perception module, an optimization control module and a decision switching module.

[0097] The detection and perception module includes a target detection module and a motion perception module. The target detection module uses sonar, camera, altimeter and other sensors to detect aquaculture operation targets and the environmental information of the underwater robot; the motion perception module uses inertial navigation devices, GPS, depth meters, Doppler speed meters and other sensors to perceive the real-time position and posture of the underwater robot.

[0098] The optimization control module includes an energy consumption control module, a trajectory tracking control module and a posture control module. The energy consumption control module is used to construct an energy consumption control target model during the operation of the underwater robot; the trajectory tracking control module is used to construct a trajectory tracking control target model during the operation of the underwater robot; and the posture control module is used to construct a posture control target model during the operation of the underwater robot.

[0099] The decision switching module designs an adaptive fuzzy task switching decision according to the control task of the underwater robot and the real-time status of the underwater robot obtained by the detection and perception module, and performs online adaptive adjustment on the weight of the optimization objective function.

[0100] Figures 6 to 10 Some operation control results are shown to verify the effectiveness of the method and system proposed in this embodiment. The operation control results include evaluation of energy consumption, trajectory tracking error and attitude control.

[0101] Specifically, Figure 6 The robot's navigation trajectory in different operation modes is demonstrated. The results show that the aquaculture robot can effectively navigate between different target locations and maintain a stable trajectory under different environmental conditions; Figure 7 The robot's tracking error on three axes is shown. The results show that the robot maintains a low tracking error throughout the operation, indicating that the control system is capable of achieving high-precision trajectory tracking; Figure 8 The energy consumption of the robot in different operation stages is shown. The results show that the energy consumption shows obvious differences in different operation modes, and the energy consumption control effect is obvious in the return stage; Fig. 9 and Fig.10 The robot's posture changes during operation are shown. The results show that the posture can be maintained in a stable range in different operation stages, verifying the effectiveness of the posture control module.

[0102] Fig.11 The task switching decision maker adaptively adjusts the weight of the optimization objective function under different working conditions. The results show that the decision maker can dynamically adjust the control weight according to the real-time status and job requirements to achieve adaptive control.

[0103] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0104] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0105] The disclosed embodiments are described above to enable any person skilled in the art to implement or use the present invention. Various modifications of these embodiments are obvious to those skilled in the art, and the general principles defined herein may also be applied to other embodiments without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0106] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

[0107] Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0108] The various illustrative logic blocks or units described in the embodiments of the present invention can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of the above. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0109] The steps of the method or algorithm described in the embodiments of the present invention can be directly embedded in hardware, a software module executed by a processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.

[0110] In one or more exemplary designs, the above functions described in the embodiments of the present invention can be implemented in hardware, software, firmware or any combination of the three. If implemented in software, these functions can be stored on a computer-readable medium, or transmitted in the form of one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. The storage medium can be any available medium that can be accessed by any general or special computer. For example, such computer-readable media can include but are not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store program codes in the form of instructions or data structures and other forms that can be read by general or special computers, or general or special processors. In addition, any connection can be appropriately defined as a computer-readable medium, for example, if the software is transmitted from a website site, server or other remote resource through a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disk and disc include compact disk, laser disk, optical disk, DVD, floppy disk and blue-ray disk. Disks usually copy data magnetically, while discs usually copy data optically with lasers. The above combination can also be included in computer readable media.

[0111] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A variable working condition control method for an underwater robot for aquaculture, characterized by: The following steps are involved: Step S1: taking several control input increments of the underwater robot as optimization targets, setting control weights of several optimization targets based on the state parameters of the underwater robot, and constructing a weight adjustment rule table according to the mapping relationship between the state parameters and the control weights. The state parameters include speed, depth from the seabed and task type. The expression of the weight adjustment rule table is: Where T is the mission type of the underwater robot; u is the speed; d is the depth from the seabed; w E is the weight of the energy consumption control cost function, w P is the trajectory tracking cost function, w A is the posture control cost function; w D is the vertical error weight; NB is negative and large; NS is negative and small; PS is positive and small; PB is positive and large; SLOW is low speed; FAST is high speed; S is low; M is medium; L is high; Step S2: Collect the state parameters of the underwater robot, search the control weights corresponding to the state parameters in the weight adjustment rule table, construct an optimization objective function, calculate the minimum value of the optimization objective function, obtain the optimal control input increment of the underwater robot, apply the control input at the current moment to the underwater robot, and drive the underwater robot to perform the control task. The expression of the optimization objective function is: J O (k)=J E (k)·w E (k)+J P (k)·w P (k)+J A (k)·w A (k); s.t.u min ≤u(k+i)≤u max In the above formula, J O (k) is the optimization objective function; J E (k) is the energy consumption control cost function; J P (k) is the trajectory tracking cost function; J A (k) is the posture control cost function; w E (k), w P (k) and w A (k) are J E (k), J P (k), J A (k) weight; Nc is the control time domain; k E is the initial weight coefficient of the energy consumption control cost function; u() is the increment of the control input; u max and u min Respectively represent the upper and lower limits of the control input; Q is the weight coefficient matrix; Np is the prediction time domain; w D is the gain coefficient of the vertical error; s(k+i|k) is the predicted path coordinate; s d (k+i|k) is the reference path coordinate, x(k+i|k), y(k+i|k), z(k+i|k) represent the x, y, and z axis coordinates of the predicted path respectively; d (k+i), y d (k+i), z d (k+i) represents the x, y, and z axis coordinates of the reference path respectively; z max and z min Respectively represent the upper and lower limits of the z-axis direction; φ(k+i|k) represents the roll angle at time k+i predicted at time k; P1 and P2 are weights; Np is the prediction time domain; is a slack variable, i = 1, 2, 3, 4; φ max ,φ min ,θ max ,θ min The upper and lower limits of the soft constraints for roll and pitch attitude; are the upper and lower limits of the hard constraints of the roll and pitch attitudes; λ is a binary switch signal; It is the logical inversion of λ. For example, when λ=1, When λ=0, Step S3: updating the state parameters of the underwater robot in real time; Step S4: Repeat steps S2 to S3 until the underwater robot completes the predetermined control task.

2. The variable working condition control method of an aquaculture underwater robot according to claim 1, characterized in that: The step S1 of constructing a weight adjustment rule table according to the mapping relationship between state parameters and control weights includes the following steps: taking the speed, depth from the seabed and task type of the underwater robot as input, taking the weight of the optimization target as output, listing all combinations of speed, depth from the seabed and task type, setting the control weight of each combination, and obtaining a weight adjustment rule table.

3. The variable working condition control method of an aquaculture underwater robot according to claim 2, characterized in that: The step of setting the control weight of each combination comprises the following steps: Step S11: define the fuzzy sets of each fuzzy variable, the input fuzzy variables include speed, depth from the seabed and task type, the output fuzzy variable is weight, the fuzzy set of speed is low speed SLOW and high speed FAST, the fuzzy set of depth from the seabed is low S, medium M, high L, the fuzzy set of task type is 0, 1, 2, 3, where the diving stage is defined as 0, the search operation stage is defined as 1, the precision operation stage is defined as 2, and the return stage is defined as 3, and the fuzzy sets of each weight are: small, medium, and large; Step S12: creating a membership function for each fuzzy variable, converting the actual value of the fuzzy variable into the membership value of the fuzzy set; Step S13: Setting fuzzy rules to map the fuzzy set of input fuzzy variables to the fuzzy set of output fuzzy variables.

4. The variable working condition control method of an aquaculture underwater robot according to claim 3, characterized in that: In step S12, the membership function of the speed u is set as: The membership function of the depth d from the seabed is set as: The membership function of task type T is set as: Among them, NB is negative and large; NS is negative and small; PS is positive and small; PB is positive and large.

5. The variable working condition control method of an aquaculture underwater robot according to claim 1, characterized in that: In step S2, the minimum value of the optimization objective function is calculated by the Casadi solver, including the following steps: Step S21: configure the Casadi solver, set the target optimization function as the objective function, the constraint of the energy consumption control cost function as the input constraint, the constraints of the trajectory tracking cost function and the attitude control cost function as the state constraint, and set the solution method to the interior point method; Step S22: Call the Casadi solver to execute the optimization solution process until the set maximum number of iterations is reached.

6. A variable working condition operation control system for an aquaculture underwater robot, which is implemented based on a variable working condition operation control method for an aquaculture underwater robot as claimed in any one of claims 1 to 5, characterized in that: It includes detection and perception module, optimization control module and decision-making switching module; The detection and perception module includes a target detection module and a motion perception module. The target detection module is used to detect the aquaculture operation target and the environmental information of the underwater robot; the motion perception module is used to perceive the real-time position and posture of the underwater robot; The optimization control module includes an energy consumption control module, a trajectory tracking control module and a posture control module. The energy consumption control module is used to construct an energy consumption control target model during the operation of the underwater robot; the trajectory tracking control module is used to construct a trajectory tracking control target model during the operation of the underwater robot; the posture control module is used to construct a posture control target model during the operation of the underwater robot; The decision switching module designs an adaptive fuzzy task switching decision according to the control task of the underwater robot and the real-time state of the underwater robot obtained by the detection and perception module, and performs online adaptive adjustment on the weight of the optimization objective function.

Images