A motor coordinated control method and system for an underwater towing cable device

Abstract

The present application discloses a motor coordination control method and system for an underwater towing cable device, and relates to the field of motor control technology. The motor coordination control method for the underwater towing cable device comprises: obtaining the horizontal motion control data of each motor wing; obtaining the current reward value of the first motor wing based on the control data; obtaining the interference possibility data of the first motor wing based on the control data; obtaining the target reward value of the first motor wing based on the current reward value and the interference possibility data; inputting the target reward value into a Q learning model to automatically adjust the control parameters of the PID controller of the first motor wing. The present application realizes efficient control of the motor coordination control system for the horizontal motion of the underwater towing cable device (i.e., the acquisition of the reward value) by designing a coordinated control reward rule for the horizontal motion of the underwater towing cable device (i.e., the three-wing towing device), and automatically adjusting the PID parameter combination based on the Q learning model.

Description

Technical Field

[0001] The present application relates to the technical field of motor control, and in particular to a motor coordinated control method and system for an underwater towing cable device. Background Art

[0002] When using a towing vessel to lay multiple cables underwater simultaneously, the three-dimensional posture of each cable needs to be controlled. Figure 6 As shown, the purpose of controlling the three-dimensional posture of each cable includes at least: preventing a single cable from being twisted and damaged; preventing the spacing between adjacent cables (i.e., Figure 6 The distance D shown is too short, resulting in entanglement and damage. In the prior art, there are various tools for controlling the three-dimensional posture of cables, and the commonly used ones are as follows Figure 3 The three-wing tug shown in the figure includes three evenly distributed motorized wings. When in use, the three-wing tug is connected to the cable. When the towing ship tows the cable, the motorized wings on the three-wing tug form different shapes, which can control the depth, rotation and horizontal movement of the cable. Since the three-wing tug is a mature technology, it will not be described in detail here.

[0003] It should be noted that controlling the horizontal movement of the cable through the three-wing towed device is crucial for underwater towing cables. Because the horizontal movement of the three-wing towed device directly affects the stability of the towed cable and the heading of the towed ship, precise horizontal motion control can ensure that the towed cable moves smoothly on the predetermined trajectory, reduce the swing and interference of the towed cable, and thus improve the overall maneuverability and towing efficiency. In the prior art, the PID control algorithm is generally used to effectively control the horizontal movement of the underwater towed cable by adjusting the angles of each motorized wing of the three-wing towed device in real time. The PID control algorithm works together through the three functions of proportion, integration and differentiation to ensure that the towed cable can stably and accurately maintain the predetermined trajectory in various underwater environments. This can significantly improve the operating efficiency and safety of the towing system.

[0004] The prior art optimizes the gain parameters of the PID controller based on the Q learning model. By defining the state space, action space and reward function, and using the Q learning model for training and adjustment, the optimal PID parameter combination suitable for the system can be found, thereby improving the motor coordination control system of the underwater towing device. However, when defining reward rules based on Q learning, they are generally some general methods, such as: some fluctuation errors of the system, input control smoothness, etc. The reward values ​​obtained based on these reward rules cannot effectively reward the coordinated control of the horizontal motion of each three-wing towing device, which makes it difficult for the Q learning model to effectively learn the optimal parameters of PID control. Summary of the invention

[0005] The purpose of the present application is to provide a motor coordinated control method and system for an underwater towing cable device, so as to solve the problem that the reward value obtained by the prior art reward rule is difficult to enable the Q learning model to effectively learn the optimal parameters of PID control.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] In a first aspect, the present application proposes a motor coordinated control method for an underwater towing cable device, wherein the underwater towing cable device includes a plurality of three-wing towing devices, each of which includes three evenly distributed motorized wings, and each motorized wing is adjusted and controlled by a PID controller. The motor coordinated control method for the underwater towing cable device includes:

[0008] Acquire horizontal motion control data of each motor wing; the control data at least includes time-series angle data and time-series position data of each motor wing;

[0009] Based on the control data, a current reward value of a first motor wing is obtained; the first motor wing is any one of the motor wings;

[0010] Based on the control data, interference possibility data of the first motor wing is acquired; the interference possibility data is at least used to characterize the possibility of the first motor wing changing its position due to the impact of the waves at the current time;

[0011] Based on the current reward value and the interference possibility data, obtaining a target reward value of the first motor wing;

[0012] The target reward value is input into a Q learning model to automatically adjust control parameters of a PID controller of the first motor wing.

[0013] As a specific solution in the technical solution of the present application, the obtaining of the current reward value of the first motor wing based on the control data includes:

[0014] The central axis of the first motorized wing is projected onto a first plane to obtain a first straight line; the first plane is perpendicular to the axis of the first three-wing tug; the first motorized wing is located on the first three-wing tug;

[0015] Projecting a spatial straight line onto the first surface to obtain a second straight line; the spatial straight line is parallel to the vertical direction;

[0016] Obtaining a first reward value based on a first angle formed by the first straight line and the second straight line;

[0017] Based on the first reward value, a current reward value of the first motor wing is obtained.

[0018] As a specific solution in the technical solution of the present application, the obtaining of the current reward value of the first motor wing based on the first reward value includes:

[0019] Projecting the central axes of the second motor wing and the third motor wing onto the first plane to obtain a third straight line and a fourth straight line; the first motor wing, the second motor wing and the third motor wing are motor wings located on the first three-wing dragger and are different from each other;

[0020] Based on the first straight line and the third straight line, obtaining a second angle;

[0021] Based on the first straight line and the fourth straight line, obtaining a third angle;

[0022] A current reward value of the first motor wing is acquired based on the first reward value, the second angle, and the third angle.

[0023] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the current reward value of the first motor wing based on the first reward value, the second angle and the third angle is as follows:

[0024] ;

[0025] in, Represents the current reward value of the Ath motor wing among all motor wings; represents the first reward value of the Ath motor wing; represents the second angle; represents the third angle; Represents any positive number greater than or equal to 0; Indicates finding the absolute value.

[0026] As a specific solution in the technical solution of the present application, the obtaining of interference possibility data of the first motor wing based on the control data includes:

[0027] Based on the control data, a first change distance, a second change distance and a third change distance are obtained; the first change distance is the distance between the current time sequence position and the previous time sequence position of the first motor wing; the second change distance is the distance between the current time sequence position and the previous time sequence position of the second motor wing; the third change distance is the distance between the current time sequence position and the previous time sequence position of the third motor wing; the first motor wing, the second motor wing and the third motor wing are motor wings located on the same three-wing tug and are different from each other;

[0028] Based on the first change distance, the second change distance, and the third change distance, interference possibility data of the first motor wing is acquired.

[0029] As a specific solution in the technical solution of the present application, the obtaining of the target reward value of the first motor wing based on the current reward value and the interference possibility data includes:

[0030] Based on the current reward value and the interference possibility data, obtaining a second reward value;

[0031] Based on the second reward value, a target reward value of the first motor wing is obtained.

[0032] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the second reward value based on the current reward value and the interference possibility data is as follows:

[0033] ;

[0034] in, represents the second reward value of the Ath motor wing among all motor wings; m represents that the Ath motor wing has experienced m time series in total; exp represents an exponential function with e as the base; represents the interference possibility data of the Ath maneuvering wing at the i-th time sequence; Represents the current reward value of the Ath motor wing at the i-th time sequence.

[0035] As a specific solution in the technical solution of the present application, obtaining the target reward value of the first motor wing based on the second reward value includes:

[0036] Based on the control data, a time sequence distance between a first three-wing tug and a second three-wing tug is acquired; the first motorized wing is located on the first three-wing tug; the second three-wing tug is any three-wing tug among the three-wing tugs that is different from the first three-wing tug;

[0037] Based on the time series distance and the second reward value, a target reward value of the first motor wing is obtained.

[0038] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the target reward value of the first motor wing based on the time series distance and the second reward value is as follows:

[0039] ;

[0040] ;

[0041] in, represents the target reward value of the Ath maneuvering wing among all maneuvering wings; exp represents the exponential function with e as the base; v represents the number of three-wing draggers, and v is greater than or equal to 2; represents the average time sequence distance between the i-th three-wing tug and the j-th three-wing tug among the three-wing tugs, and the A-th motorized wing is located at the j-th three-wing tug; represents the serial number of the j-th three-wing dragger; represents the serial number of the i-th three-wing dragger; Indicates the absolute value. Represents the second reward value of the Ath motor wing.

[0042] In a second aspect, the present application proposes a motor coordination control system for an underwater towing cable device, wherein the underwater towing cable device includes a plurality of three-wing towing devices, each of which includes three evenly distributed motor wings, each of which is adjusted and controlled by a PID controller, and the motor coordination control system for the underwater towing cable device includes:

[0043] A reader, used to obtain horizontal motion control data of each motor wing; the control data at least includes time-series angle data and time-series position data of each motor wing;

[0044] The server is configured to obtain a current reward value of a first motor wing based on the control data; the first motor wing is any one of the motor wings;

[0045] And, based on the control data, obtaining interference possibility data of the first motor wing; the interference possibility data is at least used to characterize the possibility of the first motor wing changing its position due to the impact of the waves at the current time;

[0046] and, based on the current reward value and the interference possibility data, obtaining a target reward value of the first motor wing;

[0047] And, the target reward value is input into a Q learning model to automatically adjust the control parameters of the PID controller of the first motor wing.

[0048] As a specific solution in the technical solution of the present application, the server is further used to project the central axis of the first motorized wing onto a first plane to obtain a first straight line; the first plane is perpendicular to the axis of the first three-wing tug; the first motorized wing is located on the first three-wing tug;

[0049] And, projecting the space straight line onto the first surface to obtain a second straight line; the space straight line is parallel to the vertical direction;

[0050] and, obtaining a first reward value based on a first angle formed by the first straight line and the second straight line;

[0051] And, based on the first reward value, a current reward value of the first motor wing is obtained.

[0052] As a specific solution in the technical solution of the present application, the server is further used to project the central axis of the second motor wing and the third motor wing onto the first surface to obtain a third straight line and a fourth straight line; the first motor wing, the second motor wing and the third motor wing are motor wings located on the first three-wing dragger and are different from each other;

[0053] And, based on the first straight line and the third straight line, obtaining a second angle;

[0054] And, based on the first straight line and the fourth straight line, obtaining a third angle;

[0055] And, based on the first reward value, the second angle and the third angle, a current reward value of the first motor wing is obtained.

[0056] As a specific solution in the technical solution of the present application, the server obtains the current reward value of the first motor wing based on the first reward value, the second angle and the third angle. The calculation formula is as follows:

[0057] ;

[0058] in, Represents the current reward value of the Ath motor wing among all motor wings; represents the first reward value of the Ath motor wing; represents the second angle; represents the third angle; Represents any positive number greater than or equal to 0; Indicates finding the absolute value.

[0059] As a specific solution in the technical solution of the present application, the server is further used to obtain a first change distance, a second change distance and a third change distance based on the control data; the first change distance is the distance between the current time sequence position and the previous time sequence position of the first motor wing; the second change distance is the distance between the current time sequence position and the previous time sequence position of the second motor wing; the third change distance is the distance between the current time sequence position and the previous time sequence position of the third motor wing; the first motor wing, the second motor wing and the third motor wing are motor wings located on the same three-wing tug and are different from each other;

[0060] And, based on the first change distance, the second change distance and the third change distance, interference possibility data of the first motor wing is obtained.

[0061] As a specific solution in the technical solution of the present application, the server is further used to obtain a second reward value based on the current reward value and the interference possibility data;

[0062] And, based on the second reward value, a target reward value of the first motor wing is obtained.

[0063] As a specific solution in the technical solution of the present application, the server obtains the calculation formula of the second reward value based on the current reward value and the interference possibility data as follows:

[0064] ;

[0065] in, represents the second reward value of the Ath motor wing among all motor wings; m represents that the Ath motor wing has experienced m time series in total; exp represents an exponential function with e as the base; represents the interference possibility data of the Ath maneuvering wing at the i-th time sequence; Represents the current reward value of the Ath motor wing at the i-th time sequence.

[0066] As a specific solution in the technical solution of the present application, the server is further used to obtain the time sequence distance between the first three-wing tug and the second three-wing tug based on the control data; the first motorized wing is located on the first three-wing tug; the second three-wing tug is any three-wing tug among the three-wing tugs that is different from the first three-wing tug;

[0067] And, based on the time series distance and the second reward value, a target reward value of the first motor wing is obtained.

[0068] As a specific solution in the technical solution of the present application, the server obtains the target reward value of the first motor wing based on the time series distance and the second reward value. The calculation formula is as follows:

[0069] ;

[0070] ;

[0071] in, represents the target reward value of the Ath maneuvering wing among all maneuvering wings; exp represents the exponential function with e as the base; v represents the number of three-wing draggers, and v is greater than or equal to 2; represents the average time sequence distance between the i-th three-wing tug and the j-th three-wing tug among the three-wing tugs, and the A-th motorized wing is located at the j-th three-wing tug; represents the serial number of the j-th three-wing dragger; represents the serial number of the i-th three-wing dragger; Indicates the absolute value. Represents the second reward value of the Ath motor wing.

[0072] Compared with the prior art, the beneficial effects of this application are:

[0073] The present application reduces the influence of the reward value of the control data affected by waves and wind and waves through interference possibility data, so that the coordinated control reward rule (that is, the acquisition of the reward value) of the horizontal movement of the underwater towing cable device (that is, the three-wing towing device) designed in the present application can more accurately reflect the effect of the actual control adjustment of the PID controller, and then based on the Q learning model, the Q learning model can effectively learn the optimal parameters of the PID control. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A flow chart of a motor coordination control method for an underwater towing cable device proposed in an embodiment of the present application;

[0075] Figure 2 A schematic diagram of the structure of a motor coordination control system for an underwater towing cable device proposed in an embodiment of the present application;

[0076] Figure 3 A three-wing tug in the prior art;

[0077] Figure 4 for Figure 3 Schematic diagram of the state of the middle three-wing dragger performing horizontal movement;

[0078] Figure 5 A schematic diagram of projecting the central axis of the motor wing of the three-wing tug onto the first surface according to an embodiment of the present application;

[0079] Figure 6 It is a top view schematic diagram of the towing cable of the towing ship;

[0080] In the figure: 1. three-wing tug; 11. connecting pipe; 12. motor wing; 21. first projection straight line; 22. second projection straight line; 23. third projection straight line; 3. fourth projection straight line; 4. towing vessel; 5. cable. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0082] The terms "first", "second", etc. in the description of the embodiment of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, such as the first motor wing and the second motor wing proposed below, which belong to different motor wings. It should be understood that the motor wings used in this way can be interchanged where appropriate, so that the embodiments described here can be implemented in an order other than the content illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of modules that appear in the embodiment of the present application is only a logical division. There may be other division methods when implemented in actual applications, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in the embodiment of the present application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0083] In order to solve the technical problem that the reward value obtained by the prior art reward rules proposed in the background art is difficult to make the Q learning model effectively learn the optimal parameters of PID control, this application proposes a motor coordination control method for an underwater towing cable device, wherein the underwater towing cable device includes a plurality of three-wing towing devices, each of which includes three evenly distributed motor wings, and each motor wing is adjusted and controlled by a PID controller. Since the three-wing towing device is a mature technology, it will not be described in detail. Figure 1 As shown, in this embodiment, the motor coordinated control method of the underwater towing cable device includes steps S100 to S500.

[0084] Step S100: Acquire the horizontal motion control data of each motor wing.

[0085] It should be noted that in the embodiments of the present application, Figure 3As shown, the three-wing tug 1 is composed of a connecting tube 11 and three motor wings 12, and the three motor wings 12 are evenly distributed around the circumference of the connecting tube 11. In this embodiment, the control of each motor wing 12 is based on the PID control algorithm, so a PID controller is installed on each motor wing 12. It should be understood that the PID control algorithm and the PID controller are both mature technologies and will not be described in detail here.

[0086] It should be noted that in the process of using the Q learning model to optimize the PID parameters, it is necessary to determine the reward rules so that each motor wing 12 can determine the reward value based on the action or state it will perform in the future. The reward value is then input into the Q learning model so that the Q learning model can quickly learn the optimal parameters for PID control. Therefore, it is necessary to determine the state space and action space of the Q learning model. In this embodiment, the state space set is: the current three gain parameters of PID (proportional parameter, integral parameter, differential parameter), the angle, speed, acceleration, etc. of the motor wing; the action space is set to (the action is the operation that the three-wing dragger 1 can take. For the PID controller, the action mainly involves the adjustment of the PID gain parameters): the three gain parameter values ​​adjusted each time are specifically the following:

[0087] 1. Only adjust the scale parameter by +0.1;

[0088] 2. Only adjust the integral parameter +0.1;

[0089] 3. Only adjust the differential parameter +0.1;

[0090] 4. Adjust the ratio, differential parameter +0.1;

[0091] 5. Adjust the ratio, integral parameter +0.1;

[0092] 6. Adjust the integral and differential parameters by +0.1;

[0093] 7. Adjust the proportional, integral, and differential parameters to +0.1.

[0094] It should be clear that in other embodiments of the present application, the state space and the action space can be set according to actual needs. In other words, in the embodiments of the present application, no restrictions are imposed on the state space and the action space.

[0095] In an embodiment of the present application, the control data may be any data related to the action and state of the motor wing. For example, the control data may include at least the time-series angle data and the time-series position data of each motor wing.

[0096] Step S200: Based on the control data, a current reward value of the first motor wing is obtained.

[0097] It should be clear that if the three-wing tug is to be controlled to perform horizontal movement, the three motorized wings 12 of the three-wing tug 1 need to be shaped as follows: Figure 4 shown. Figure 4 The moving direction of the towboat (i.e. Figure 6 Direction C in the figure is perpendicular to the paper plane and points from the inside of the paper plane to the outside of the paper plane; if the three-wing dragger 1 becomes as Figure 4 In the form shown, each motorized wing 12 in the three-wing tug 1 can move in the horizontal direction (i.e., as shown in FIG. Figure 4 If the three-wing tug 1 is to be moved in the Y direction (i.e., the vertical direction), the form of each motorized wing 12 on the three-wing tug 1 needs to be changed. It should be understood that the motorized wing 12 on the three-wing tug 1 is changed into different forms, and the three-wing tug 1 can perform corresponding actions (e.g., horizontal movement, vertical movement, or rotation, etc.), which is a mature technology and will not be described in detail here.

[0098] In the embodiment of the present application, the state and action of each motorized wing 12 on the three-wing tug 1 need to be precisely controlled in order to enable the three-wing tug 1 to perform precise horizontal movement. In this embodiment, the first motorized wing is any one of the motorized wings.

[0099] As can be seen from the foregoing, we imagine the motorized wing 12 on each three-wing tug 1 as a straight line. If the three-wing tug 1 is to accurately move horizontally, the straight line formed by one motorized wing 12 in the three-wing tug 1 should be parallel to the vertical direction, and the angles between the straight lines formed by the three motorized wings 12 are all 120° (hereinafter referred to as the ideal state). In actual situations, it is difficult to adjust the three motorized wings 12 on the three-wing tug 1 to the ideal state through the PID controller. In other words, in this embodiment, if the PID controller is controlling the three-wing tug 1 to move horizontally, one of the adjustment strategies makes the state of the three-wing tug 1 closer to the ideal state, then it can be considered that the reward value of the adjustment strategy is higher.

[0100] In the embodiment of the present application, in order to effectively reward the coordinated control of the horizontal motion of the three-wing tug, the following method can be used: Figure 4 The size of the state difference shown is used to obtain the corresponding reward value. In other words, if the three-wing dragger after coordinated control by the PID controller is closer to Figure 4 The state shown, the higher the reward value can be; if the three-wing dragger after coordinated control by the PID controller is closer to Figure 4 The higher the status shown, the lower the reward value can be.

[0101] In an embodiment of the present application, any suitable method may be used to obtain the current reward value of the first motor wing based on the control data. For example, in one embodiment of the present application, step S200, based on the control data, obtains the current reward value of the first motor wing, including steps S210 to S240.

[0102] Step S210: Projecting the central axis of the first motor wing onto the first surface to obtain a first straight line.

[0103] In this embodiment, the first surface is perpendicular to the axis of the first three-wing dragger (i.e. Figure 4 The first motor wing is located on the first three-wing dragger. Figure 5 As shown, in this embodiment, the first straight line may be any one of the first projection straight line 21 , the second projection straight line 22 and the third projection straight line 23 .

[0104] Step S220: Project the spatial straight line onto the first surface to obtain a second straight line, where the spatial straight line is parallel to the vertical direction.

[0105] In the embodiment of the present application, the second straight line can be as follows Figure 5 As shown in the fourth projection straight line 3.

[0106] Step S230: obtaining a first reward value based on a first angle formed by the first straight line and the second straight line.

[0107] From the above, we can know that if the first three-wing dragger is in an ideal state, then Figure 5 As shown, the angle formed by the first projection line 21 and the fourth projection line 3 is 180°; the angle formed by the second projection line 22 and the fourth projection line 3 is 60°; the angle formed by the third projection line 23 and the fourth projection line 3 is 300°. In other words, if the first three-wing tug is closer to the ideal state, the first angle should be closer to an integer multiple of 60°. In other words, if the first angle is closer to an integer multiple of 60°, it can be considered that the first motor wing on the first three-wing tug is closer to the ideal state, that is, the first reward value should be higher, otherwise, the first reward value should be lower.

[0108] Specifically, in the embodiment of the present application, in step S230, based on the first angle formed by the first straight line and the second straight line, a calculation formula for obtaining the first reward value is as follows:

[0109] ;

[0110] in, represents the first reward value of the Ath motor wing (that is, the first motor wing) among all motor wings; represents the first angle; It represents the exponential function with the natural constant e as the base; represents the minimum value; k represents a constant, and k is any one of 0, 1, 2, 3, 4, 5 and 6. It is easy to understand that if the first angle The closer it is to an integer multiple of 60°, the The smaller it is, the first reward value obtained later The bigger.

[0111] Step S240: Based on the first reward value, obtain a current reward value of the first motor wing.

[0112] In the embodiment of the present application, the first reward value can be used as the current reward value of the first motor wing. However, it should be clear that if the first three-wing tug is in an ideal state, the first angle must be close to an integer multiple of 60°. However, the fact that the first angle is close to an integer multiple of 60° does not mean that the first three-wing tug is in an ideal state. As can be seen from the foregoing, if the first three-wing tug is in an ideal state, the first angle must be close to an integer multiple of 60°, and if Figure 5 As shown, the angle between any two of the first projection line 21, the second projection line 22 and the third projection line 23 must also be close to 120°. In order to obtain a more accurate reward value, in one embodiment of the present application, step S240, based on the first reward value, obtains the current reward value of the first motor wing, including steps S241 to S244.

[0113] Step S241: projecting the central axes of the second motor wing and the third motor wing onto the first surface to obtain a third straight line and a fourth straight line.

[0114] In an embodiment of the present application, the first motor wing, the second motor wing and the third motor wing are motor wings located on the first three-wing tug and are different from each other. Figure 5 As shown, it is assumed that the first straight line is the first projection straight line 21 ; the third straight line is the second projection straight line 22 ; and the fourth straight line is the third projection straight line 23 .

[0115] Step S242: Based on the first straight line and the third straight line, obtain a second angle.

[0116] In this embodiment, the second angle is Figure 5 Angle b shown.

[0117] Step S243: Based on the first straight line and the fourth straight line, obtain a third angle.

[0118] In this embodiment, the third angle is Figure 5 Angle a shown.

[0119] Step S244: acquiring a current reward value of the first motor wing based on the first reward value, the second angle and the third angle.

[0120] It is easy to understand that, from the foregoing, the closer the second angle and the third angle are to 120°, the closer the first three-wing dragger is to the ideal state. In other words, the closer the second angle and the third angle are to 120°, the greater the reward value should be, otherwise, the smaller the reward value should be.

[0121] In an embodiment of the present application, any method may be used to obtain the current reward value of the first motor wing based on the first reward value, the second angle, and the third angle. For example, in a specific embodiment of the present application, in step S244, the calculation formula for obtaining the current reward value of the first motor wing based on the first reward value, the second angle, and the third angle is as follows:

[0122] ;

[0123] in, Indicates the current reward value of the Ath motor wing (that is, the first motor wing) among all motor wings; represents the first reward value of the Ath motor wing; represents the second angle; represents the third angle; Represents any positive number greater than or equal to 0; It should be clear that in the embodiment of the present application, if the difference between the second angle and the third angle and 120° is larger, the denominator is larger, that is, the current reward value is smaller; if the difference between the second angle and the third angle and 120° is smaller, the denominator is smaller, that is, the current reward value is larger.

[0124] It should be clear that in some cases, if there are waves or wind waves that interfere with the shape of the first three-wing tug, it may cause the first motor wing to be in a shape that is not controlled by the PID controller (for example, the current angle and spatial position of the first motor wing). In other words, if there are waves or wind waves, the horizontal motion control data of each motor wing is inaccurate, so the reward value obtained based on the horizontal motion control data of each motor wing must also be inaccurate. For example, according to the current PID control strategy, the first three-wing tug can be adjusted to the following shape: Figure 4 The ideal state shown in the figure (that is, the reward value should be large), but due to the influence of wind and waves, the first three-wing tug is far from the ideal state, which makes the actual reward value small. Alternatively, according to the current PID control strategy, adjust the first three-wing tug to Figure 4The ideal state shown is far away from the target state (that is, the reward value should be small), but due to the influence of wind and waves, the first three-wing tug is far away from the ideal state, which makes the actual reward value larger.

[0125] In order to obtain a more accurate reward value, in an embodiment of the present application, the possibility of interference from waves or wind waves is determined. Specifically, the possibility of interference from waves or wind waves is the possibility that the first motor wing will change position due to the impact of waves at the current time. If the possibility of interference from waves or wind waves at the current moment is large, the reward value at the interfered moment should be reduced to reduce the impact of erroneous data on the Q learning model; if the possibility of interference from waves or wind waves at the current moment is small, the reward value at the undisturbed moment should be amplified to enhance the impact of correct data on the Q learning model.

[0126] Step S300: Based on the control data, obtaining interference possibility data of the first motor wing.

[0127] In an embodiment of the present application, the interference possibility data is at least used to characterize the possibility of the first motor wing being impacted by waves and causing a position change at the current time.

[0128] It should be clear that in the process of controlling the three-wing tug 1 to move horizontally, it can be known from the foregoing that the angle formed by each motorized wing 12 on the three-wing tug 1 is basically 120°, that is, the relative position of each motorized wing 12 will not change. If the relative position of each motorized wing 12 changes, it means that the three-wing tug 1 is highly likely to be impacted by waves or wind and waves. Therefore, in the embodiment of the present application, it can be determined whether the three-wing tug 1 is impacted by waves or wind and waves based on the time sequence position change of each motorized wing 12 on the three-wing tug 1. It is easy to understand that if the time sequence movement distance difference of each motorized wing 12 on the three-wing tug 1 is smaller, it means that the probability of the three-wing tug 1 being impacted by waves or wind and waves is smaller; if the time sequence movement distance difference of each motorized wing 12 on the three-wing tug 1 is larger, it means that the probability of the three-wing tug 1 being impacted by waves or wind and waves is greater.

[0129] In an embodiment of the present application, the interference possibility data of the first motor wing can be obtained in any suitable manner based on the control data. For example, in an embodiment of the present application, step S300, based on the control data, obtains the interference possibility data of the first motor wing, including steps S310 to S320.

[0130] Step S310: Based on the control data, a first change distance, a second change distance and a third change distance are acquired.

[0131] Specifically, in this embodiment, the first change distance is the distance between the current time sequence position and the previous time sequence position of the first motor wing. The second change distance is the distance between the current time sequence position and the previous time sequence position of the second motor wing. The third change distance is the distance between the current time sequence position and the previous time sequence position of the third motor wing. The first motor wing, the second motor wing and the third motor wing are motor wings located on the same three-wing tractor and are different from each other.

[0132] Step S320: Obtain interference possibility data of the first motor wing based on the first change distance, the second change distance and the third change distance.

[0133] It is easy to understand that in the absence of wind or waves, the first change distance, the second change distance and the third change distance are basically the same, that is, the changes of the motor wings on the same three-wing tug are basically the same. In an embodiment of the present application, the interference possibility data of the first motor wing can be obtained based on any suitable method through the first change distance, the second change distance and the third change distance. For example, in one embodiment of the present application, the sum of the first change distance, the second change distance and the third change distance is used as the interference possibility data. In another embodiment of the present application, step S320, based on the first change distance, the second change distance and the third change distance, the calculation formula for obtaining the interference possibility data of the first motor wing is as follows:

[0134] ;

[0135] in, Indicates the interference possibility data of the Ath motor wing (i.e., the first motor wing) among the motor wings; represents the first change distance; represents the second change distance; represents the third change distance; represents the absolute value; exp represents the exponential function with the natural constant e as the base. If the distance between the timing positions of the first motor wing and the distance between the timing positions of the other two motor wings on the first three-wing tug are larger, the possibility that the first motor wing is disturbed by sea waves or wind waves is also greater.

[0136] Step S400: acquiring a target reward value of the first motor wing based on the current reward value and the interference possibility data.

[0137] As can be seen from the foregoing, in an embodiment of the present application, the current reward value can be corrected by the interference possibility data to obtain a more accurate target reward value. In an embodiment of the present application, the target reward value of the first motor wing can be obtained based on the current reward value and the interference possibility data in any manner. For example, in one embodiment of the present application, the current reward value and the inverse of the interference possibility data can be directly multiplied to obtain the target reward value of the first motor wing. In another embodiment of the present application, step S400, based on the current reward value and the interference possibility data, obtains the target reward value of the first motor wing, includes step S410.

[0138] Step S410: acquiring a second reward value based on the current reward value and the interference possibility data;

[0139] It should be clear that in this embodiment, based on the current reward value and the interference possibility data, the calculation formula for obtaining the second reward value is as follows:

[0140] ;

[0141] in, represents the second reward value of the Ath motor wing (i.e., the first motor wing) among all motor wings; m represents that the Ath motor wing has experienced m time series in total; exp represents an exponential function with the natural constant e as the base; represents the interference possibility data of the Ath maneuvering wing at the i-th time sequence; represents the current reward value of the Ath motor wing at the i-th time sequence. In this embodiment, the above formula reduces the reward value when it is disturbed by wind or waves, and increases the reward value when it is not disturbed by wind or waves. In the embodiment of the present application, the above second reward value can be Directly used as the target reward value of the first maneuvering wing.

[0142] However, it should be clear that the purpose of controlling the three-wing dragger to move horizontally is to control Figure 5 The spacing between the three-wing tugs 1 shown in the figure is to avoid entanglement or collision of the cables 5 on each three-wing tug 1. That is to say, in the embodiment of the present application, it can also be considered that the PID control strategy of the first motor wing can control the first motor wing so that the first three-wing tug always maintains a fixed distance with other three-wing tugs. If the fixed distance can be maintained, the reward value should be increased, and if not, the reward value should be reduced.

[0143] Therefore, in an embodiment of the present application, step S400, obtaining a target reward value of the first motor wing based on the current reward value and the interference possibility data, may also include step S420.

[0144] Step S420: Based on the second reward value, obtain a target reward value of the first motor wing.

[0145] In an embodiment of the present application, the second reward value can be adjusted based on the variance or standard deviation of the time series distance between the first three-wing tug and the other three-wing tugs, thereby obtaining the target reward value of the first motor wing. If the variance or standard deviation is larger, it means that the current control strategy is more difficult to keep the distance between the first three-wing tug and the other three-wing tug fixed, that is, the reward value needs to be reduced; if the variance or standard deviation is smaller, it means that the current control strategy is more able to keep the distance between the first three-wing tug and the other three-wing tug fixed, that is, the reward value needs to be increased.

[0146] It should be clear that the prior art cannot obtain the spatial position of the three-wing tug itself, and can only obtain the spatial position of each motorized wing on the three-wing tug. If the spatial position of the three-wing tug itself cannot be obtained, the distance between each three-wing tug cannot be obtained. In order to obtain the spatial position of the three-wing tug itself, the average value of the spatial positions of the three motorized wings on the three-wing tug can be used as the spatial position of the three-wing tug itself. It is easy to understand that obtaining the average value of three coordinate points in the spatial coordinate is a mature technology and will not be described in detail here.

[0147] In another embodiment of the present application, step S420, based on the second reward value, obtaining the target reward value of the first motor wing, includes steps S421 to S422.

[0148] Step S421: Based on the control data, the time sequence distance between the first three-wing tug and the second three-wing tug is obtained.

[0149] It should be clear that the first motorized wing is located on the first three-wing tug; the second three-wing tug is any three-wing tug among the three-wing tugs that is different from the first three-wing tug. Figure 6 The towing ship 4 shown in the figure has a total of 4 cables 5, each of which is equipped with a three-wing towed device 1. The first three-wing towed device and the second three-wing towed device are Figure 6 As shown in the figure, the time sequence distance between the first three-wing tug and the second three-wing tug at the current moment is as follows: Figure 6 The distance D is shown.

[0150] Step S422: Based on the time series distance and the second reward value, a target reward value of the first motor wing is obtained.

[0151] like Figure 6As shown, it is assumed that the distance D is the standard distance between two adjacent three-wing tractors. The ideal control state is that the distance between two adjacent three-wing tractors is the distance D at any time. It is easy to understand that it is difficult to ensure that the distance between two adjacent three-wing tractors is the distance D at every moment in reality. However, if the PID control strategy makes the distance between two adjacent three-wing tractors closer to the distance D, it means that the reward value of the control strategy should be higher. That is to say, in the embodiment of the present application, the second reward value can be adjusted based on the stability of the distance control between each three-wing tractor to obtain the target reward value.

[0152] Specifically, in one embodiment of the present application, in step S422, based on the time series distance and the second reward value, a calculation formula for obtaining the target reward value of the first motor wing is as follows:

[0153] ;

[0154] ;

[0155] in, represents the target reward value of the Ath mobile wing (i.e., the first mobile wing) among all mobile wings; exp represents an exponential function with the natural constant e as the base; v represents the number of three-wing draggers, and v is greater than or equal to 2; represents the average time sequence distance between the i-th three-wing tug (i.e., the second three-wing tug) and the j-th three-wing tug (i.e., the first three-wing tug) among the three-wing tugs, and the A-th motorized wing is located at the j-th three-wing tug; represents the serial number of the j-th three-wing dragger; represents the serial number of the i-th three-wing dragger; Indicates the absolute value. Represents the second reward value of the Ath motor wing.

[0156] Step S500: inputting the target reward value into the Q learning model to automatically adjust the control parameters of the PID controller of the first motor wing.

[0157] It should be clear that, initially, the Q learning model and the reward value in the Q table are initialized to zero. At this point, the parameters of the PID controller can be fixed values ​​that are initially set. Next, during the operation of the underwater towline, the Q learning model continuously explores different actions and updates the reward value in the Q table according to the reward rule. As the Q table is updated, the Q learning model gradually finds the optimal PID parameter setting, so that the overall performance of subsequent control (such as tracking error, stability, etc.) is optimal. Inputting the target reward value into the Q learning model so that the Q learning model can quickly obtain the optimal control parameters of the PID controller of the first motor wing is a mature technology and will not be elaborated here.

[0158] It should be clear that the embodiment of the motor coordinated control method of the underwater towing cable device proposed in the present application, by designing a coordinated control reward rule (that is, obtaining a reward value) for the horizontal movement of the underwater towing cable device (that is, the three-wing towing device), automatically adjusts the PID parameter combination based on the Q learning model, so as to realize efficient control of the motor coordinated control system of the horizontal movement of the underwater towing cable device.

[0159] After introducing the motor coordination control method of the underwater towed cable device proposed in the present application, the following introduces an embodiment of the motor coordination control system of the underwater towed cable device proposed in the present application, wherein the underwater towed cable device includes a plurality of three-wing towed devices, each of which includes three evenly distributed motor wings, each of which is adjusted and controlled by a PID controller, and the motor coordination control system of the underwater towed cable device is as follows. Figure 2 As shown, the motor coordination control system 200 of the underwater towing cable device includes:

[0160] The reader 201 is used to obtain the horizontal motion control data of each motor wing; the control data at least includes the time-series angle data and the time-series position data of each motor wing;

[0161] The server 202 is configured to obtain a current reward value of a first motor wing based on the control data; the first motor wing is any one of the motor wings;

[0162] And, based on the control data, obtaining interference possibility data of the first motor wing; the interference possibility data is at least used to characterize the possibility of the first motor wing changing its position due to the impact of the waves at the current time;

[0163] and, based on the current reward value and the interference possibility data, obtaining a target reward value of the first motor wing;

[0164] And, the target reward value is input into a Q learning model to automatically adjust the control parameters of the PID controller of the first motor wing.

[0165] As a specific embodiment of the present application, the server 202 is further used to project the central axis of the first motorized wing onto a first plane to obtain a first straight line; the first plane is perpendicular to the axis of the first three-wing tug; the first motorized wing is located on the first three-wing tug;

[0166] And, projecting the space straight line onto the first surface to obtain a second straight line; the space straight line is parallel to the vertical direction;

[0167] and, obtaining a first reward value based on a first angle formed by the first straight line and the second straight line;

[0168] And, based on the first reward value, a current reward value of the first motor wing is obtained.

[0169] As a specific embodiment of the present application, the server 202 is further used to project the central axis of the second motor wing and the third motor wing onto the first surface to obtain a third straight line and a fourth straight line; the first motor wing, the second motor wing and the third motor wing are motor wings located on the first three-wing tug and are different from each other;

[0170] And, based on the first straight line and the third straight line, obtaining a second angle;

[0171] And, based on the first straight line and the fourth straight line, obtaining a third angle;

[0172] And, based on the first reward value, the second angle and the third angle, a current reward value of the first motor wing is obtained.

[0173] As a specific embodiment of the present application, the server 202 obtains the current reward value of the first motor wing based on the first reward value, the second angle and the third angle. The calculation formula is as follows:

[0174] ;

[0175] in, Represents the current reward value of the Ath motor wing among all motor wings; represents the first reward value of the Ath motor wing; represents the second angle; represents the third angle; Represents any positive number greater than or equal to 0; Indicates finding the absolute value.

[0176] As a specific embodiment of the present application, the server 202 is further used to obtain a first change distance, a second change distance and a third change distance based on the control data; the first change distance is the distance between the current timing position and the previous timing position of the first motor wing; the second change distance is the distance between the current timing position and the previous timing position of the second motor wing; the third change distance is the distance between the current timing position and the previous timing position of the third motor wing; the first motor wing, the second motor wing and the third motor wing are motor wings located on the same three-wing tug and are different from each other;

[0177] And, based on the first change distance, the second change distance and the third change distance, interference possibility data of the first motor wing is obtained.

[0178] As a specific embodiment of the present application, the server 202 is further configured to obtain a second reward value based on the current reward value and the interference possibility data;

[0179] And, based on the second reward value, a target reward value of the first motor wing is obtained.

[0180] As a specific embodiment of the present application, the server 202 obtains the calculation formula of the second reward value based on the current reward value and the interference possibility data as follows:

[0181] ;

[0182] in, represents the second reward value of the Ath motor wing among all motor wings; m represents that the Ath motor wing has experienced m time series in total; exp represents an exponential function with e as the base; represents the interference possibility data of the Ath maneuvering wing at the i-th time sequence; Represents the current reward value of the Ath motor wing at the i-th time sequence.

[0183] As a specific embodiment of the present application, the server 202 is further used to obtain, based on the control data, a time sequence distance between a first three-wing tug and a second three-wing tug; the first motorized wing is located on the first three-wing tug; the second three-wing tug is any three-wing tug among the three-wing tugs that is different from the first three-wing tug;

[0184] And, based on the time series distance and the second reward value, a target reward value of the first motor wing is obtained.

[0185] As a specific embodiment of the present application, the server 202 obtains the target reward value of the first motor wing based on the time series distance and the second reward value by the following calculation formula:

[0186] ;

[0187] ;

[0188] in, represents the target reward value of the Ath maneuvering wing among all maneuvering wings; exp represents the exponential function with the natural constant e as the base; v represents the number of three-wing draggers, and v is greater than or equal to 2; represents the average time sequence distance between the i-th three-wing tug and the j-th three-wing tug among the three-wing tugs, and the A-th motorized wing is located at the j-th three-wing tug; represents the serial number of the j-th three-wing dragger; represents the serial number of the i-th three-wing dragger; Indicates the absolute value. Represents the second reward value of the Ath motor wing.

[0189] It should be clear that the embodiment of the motor coordination control system of the underwater towing cable device proposed in the present application, by designing a coordinated control reward rule (that is, obtaining a reward value) for the horizontal movement of the underwater towing cable device (that is, the three-wing towing device), automatically adjusts the PID parameter combination based on the Q learning model, thereby realizing efficient control of the motor coordination control system for the horizontal movement of the underwater towing cable device.

[0190] After introducing the motor coordination control system of the underwater towing cable device proposed in the present application, the following introduces a computer-readable storage medium proposed in the present application, on which a computer program is stored. When the computer program is executed by a processor, it implements the motor coordination control method of the underwater towing cable device as described in any of the above embodiments.

[0191] It should be clear that the computer-readable storage media in this application include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory, static random access memory, dynamic random access memory, other types of random access memory, read-only memory, electrically erasable programmable read-only memory, flash memory or other memory technology, read-only compact disc read-only memory, digital versatile disc or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media, such as modulated data signals and carrier waves.

[0192] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0193] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the methods, devices and equipment described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0194] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0195] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0196] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0197] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0198] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disk), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0199] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles of the present application.

Claims

1. A motor coordinated control method for an underwater towing cable device, wherein the underwater towing cable device comprises a plurality of three-wing towing devices, each of which comprises three evenly distributed motor wings, each of which is adjusted and controlled by a PID controller, characterized in that: The motor coordinated control method of the underwater towing cable device comprises: Acquire horizontal motion control data of each motor wing; the control data at least includes time-series angle data and time-series position data of each motor wing; Based on the control data, a current reward value of a first motor wing is obtained; the first motor wing is any one of the motor wings; Based on the control data, interference possibility data of the first motor wing is acquired; the interference possibility data is at least used to characterize the possibility of the first motor wing changing its position due to the impact of the waves at the current time; Based on the current reward value and the interference possibility data, obtaining a target reward value of the first motor wing; Inputting the target reward value into a Q learning model to automatically adjust control parameters of a PID controller of the first motor wing; The step of obtaining a current reward value of the first motor wing based on the control data includes: The central axis of the first motorized wing is projected onto a first plane to obtain a first straight line; the first plane is perpendicular to the axis of the first three-wing tug; the first motorized wing is located on the first three-wing tug; Projecting a spatial straight line onto the first surface to obtain a second straight line; the spatial straight line is parallel to the vertical direction; Obtaining a first reward value based on a first angle formed by the first straight line and the second straight line; Based on the first reward value, obtaining a current reward value of the first motor wing; the obtaining the current reward value of the first motor wing based on the first reward value includes: Projecting the central axes of the second motor wing and the third motor wing onto the first plane to obtain a third straight line and a fourth straight line; the first motor wing, the second motor wing and the third motor wing are motor wings located on the first three-wing dragger and are different from each other; Based on the first straight line and the third straight line, obtaining a second angle; Based on the first straight line and the fourth straight line, obtaining a third angle; A current reward value of the first motor wing is acquired based on the first reward value, the second angle, and the third angle.

2. The motor coordinated control method of the underwater towing cable device according to claim 1, characterized in that: The calculation formula for obtaining the current reward value of the first motor wing based on the first reward value, the second angle and the third angle is as follows: ； in, Represents the current reward value of the Ath motor wing among all motor wings; represents the first reward value of the Ath motor wing; represents the second angle; represents the third angle; Represents any positive number greater than or equal to 0; Indicates absolute value.

3. The motor coordinated control method of the underwater towing cable device according to claim 1, characterized in that: The obtaining, based on the control data, interference possibility data of the first motor wing comprises: Based on the control data, a first change distance, a second change distance and a third change distance are obtained; the first change distance is the distance between the current time sequence position and the previous time sequence position of the first motor wing; the second change distance is the distance between the current time sequence position and the previous time sequence position of the second motor wing; the third change distance is the distance between the current time sequence position and the previous time sequence position of the third motor wing; the first motor wing, the second motor wing and the third motor wing are motor wings located on the same three-wing tug and are different from each other; Based on the first change distance, the second change distance, and the third change distance, interference possibility data of the first motor wing is acquired.

4. The motor coordinated control method of the underwater towing cable device according to claim 3 is characterized in that: The step of obtaining a target reward value of the first motor wing based on the current reward value and the interference possibility data includes: Based on the current reward value and the interference possibility data, obtaining a second reward value; Based on the second reward value, a target reward value of the first motor wing is obtained.

5. The motor coordinated control method of the underwater towing cable device according to claim 4, characterized in that: The calculation formula for obtaining the second reward value based on the current reward value and the interference possibility data is as follows: ； in, represents the second reward value of the Ath motor wing among all motor wings; m represents that the Ath motor wing has experienced m time series in total; exp represents an exponential function with the natural constant e as the base; represents the interference possibility data of the Ath maneuvering wing at the i-th time sequence; Represents the current reward value of the Ath motor wing at the i-th time sequence.

6. The motor coordinated control method of the underwater towing cable device according to claim 4, characterized in that: The step of acquiring a target reward value of the first motor wing based on the second reward value includes: Based on the control data, a time sequence distance between a first three-wing tug and a second three-wing tug is acquired; the first motorized wing is located on the first three-wing tug; the second three-wing tug is any three-wing tug among the three-wing tugs that is different from the first three-wing tug; Based on the time series distance and the second reward value, a target reward value of the first motor wing is obtained.

7. The motor coordinated control method of the underwater towing cable device according to claim 6, characterized in that: The calculation formula for obtaining the target reward value of the first motor wing based on the time series distance and the second reward value is as follows: ； ； in, represents the target reward value of the Ath maneuvering wing among all maneuvering wings; exp represents the exponential function with the natural constant e as the base; v represents the number of three-wing draggers, and v is greater than or equal to 2; represents the average time sequence distance between the i-th three-wing tug and the j-th three-wing tug among the three-wing tugs, and the A-th motorized wing is located at the j-th three-wing tug; represents the serial number of the j-th three-wing dragger; represents the serial number of the i-th three-wing tug; Indicates the absolute value. Represents the second reward value of the Ath motor wing.

8. A motor coordination control system for an underwater towed cable device, the system being used to execute the steps of the motor coordination control method for an underwater towed cable device according to any one of claims 1 to 7, characterized in that: include: A reader for acquiring horizontal motion control data of each motor wing; The control data at least includes time-series angle data and time-series position data of each motor wing; The server is configured to obtain a current reward value of the first motor wing based on the control data; The first motorized wing is any one of the motorized wings; and, based on the control data, obtaining interference possibility data of the first motor wing; The interference possibility data is at least used to characterize the possibility of the first motor wing being impacted by waves and causing a position change at the current time; and, based on the current reward value and the interference possibility data, obtaining a target reward value of the first motor wing; And, the target reward value is input into a Q learning model to automatically adjust the control parameters of the PID controller of the first motor wing.

Images