An underwater operation power adaptive control method and system for a dredging robot

Abstract

The present invention relates to the field of power adaptive control of robots, and particularly to a method and system for power adaptive control of an underwater operation of a dredging robot. When implementing the method and system for power adaptive control of the underwater operation of the dredging robot, the present invention fully considers the complexity of underwater operations, classifies the area to be operated according to the elevation data according to the operation difficulty, adopts different power adaptive control methods for different operation difficulty levels, and utilizes the advantages of different algorithms to process different complex scenarios to solve the problem of difficult power adaptive control in the underwater operation scenario with non-linearity and multi-variable coupling.

Description

Technical Field

[0001] The present invention relates to the field of robot power adaptive control, and particularly to a method and system for underwater operation power adaptive control of a dredging robot. Background Art

[0002] In the water system context of a city, river dredging is a key link in maintaining the health of the water ecosystem. In recent years, as people's requirements for water environment quality have become higher and higher, dredging has become an "essential course" for rivers of all sizes. Too much silt deposition will not only affect water quality, but when the weather warms up slightly, the bottom mud will also turn up to the water surface, greatly reducing the visual appearance of the river. Dredging robots are widely used in the field of underwater sediment cleaning, and their core function is to complete the excavation, transportation, and treatment of silt through actuators such as robotic arms and suction devices.

[0003] The power control of traditional dredging robots is relatively simple. The power distribution modes include: the fixed power mode, which sets a constant power according to preset working conditions and cannot adapt to dynamically changing environmental parameters such as silt density and water flow velocity, easily leading to energy waste or low dredging efficiency. The manual adjustment mode relies on the experience of operators to adjust the power, with a lag in response and insufficient accuracy, making it difficult to cope with complex underwater environments. The power feedback adjustment mode is generally a simple feedback control, that is, local feedback adjustment based on a single sensor (such as motor current), lacking the ability of multi-parameter collaborative analysis and easily causing control failure due to environmental interference. Traditional power control methods cannot adapt to the changing underwater environment. For example, uneven silt distribution and undulating terrain make fixed power or extensive adjustment likely to cause motor overload or inefficient operation, especially unnecessary energy loss under light load conditions. Existing control systems mostly rely on linear algorithms and are difficult to handle non-linear and multi-variable coupled underwater operation scenarios, with limited dynamic response speed and decision-making accuracy. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for underwater operation power adaptive control of a dredging robot to solve the problems existing in the prior art.

[0005] The present invention provides a method for underwater operation power adaptive control of a dredging robot, including:

[0006] S1: Collect underwater operation data of the dredging robot, including historical operation time and the corresponding historical operation area, and determine the relationship between the historical operation time and the historical operation area;

[0007] S2: Determine the operation time of the current operation area to be worked according to the relationship between the historical operation time and the operation area, and the area of the operation area to be worked.

[0008] S3: Scan the terrain of the underwater area to be operated and estimate the operation difficulty;

[0009] S4: Based on the to-be-operated time, the area of the to-be-operated area, and the operation difficulty, establish a power distribution model for the dredging robot, and perform power adaptive control according to the distribution model.

[0010] Preferably, the dredging robot includes a control module, a propulsion device, a dredging device, a conveying device, a communication device, an auxiliary device, and a safety device; the auxiliary device includes a camera, a lighting lamp, a sonar, and a lidar; the safety device includes a floating system and a fault protection system.

[0011] Preferably, S1 further includes: The underwater operation data of the dredging robot further includes historical operation power distribution data, and a neural network power adaptive control model is established based on the historical operation time, the historical operation area, and the historical operation power distribution data.

[0012] Preferably, S3 further includes:

[0013] S31: Divide the to-be-operated area into N blocks on average, where N>4; use the lidar to measure the underwater terrain of the to-be-operated area to obtain N elevation data sets;

[0014] S32: Collect the elevation data of the lowest points in the N elevation data sets and calculate the average value to obtain the elevation calibration value T of the to-be-operated area;

[0015] S33: The control device of the dredging robot is embedded with GIS software, and based on the elevation calibration value T, a three-dimensional model of the underwater silt is built, and the volume Vn of the N to-be-operated areas is calculated;

[0016] S34: Divide the operation difficulty of the N to-be-operated areas into easy, medium, and difficult according to the volume Vn.

[0017] Preferably, S4 establishing a power distribution model for the dredging robot includes:

[0018] S41: The control module obtains the operation difficulty of the to-be-operated area;

[0019] S42: The control module distributes power according to the operation difficulty;

[0020] S43: The control module allocates a fixed power value to the auxiliary device and the safety device.

[0021] Preferably, S42 the control module distributes power according to the operation difficulty includes:

[0022] S421: When the operation difficulty is easy, based on the time to be operated and the area of the area to be operated, use the neural network power adaptive control model to determine the power adaptive control strategy;

[0023] S422: When the operation difficulty is medium, use the expert PID control model to map the time to be operated, the area of the area to be operated, and the volume Vn into power adjustment parameters, and dynamically adjust the power adaptive control strategy;

[0024] S423: When the operation difficulty is difficult, use the reinforcement learning model to take the time to be operated, the area of the area to be operated, and the volume Vn as state observation inputs, and obtain the optimal power adaptive control strategy to balance performance and energy consumption.

[0025] Preferably, the expert PID control model uses domain expert experience or machine learning dredging robot underwater operation data to generate power adaptive control rules.

[0026] Preferably, the mapping into power adjustment parameters adjusts the parameters of the expert PID control model by changing the time to be operated, the area of the area to be operated, and the volume Vn.

[0027] Preferably, the reinforcement learning model includes:

[0028] A state observation module that collects the time to be operated, the area of the area to be operated, and the volume Vn to describe the current environmental state;

[0029] An action selection module that determines the current power adaptive control strategy based on the current environmental state through a pre-determined strategy or a random strategy;

[0030] A reward feedback module that obtains a reward signal based on the feedback of the current environmental state;

[0031] A policy update module that establishes a deep neural network based on the reward signal to update the parameters of the reinforcement learning and obtain the optimal power adaptive control strategy.

[0032] According to another aspect of the present invention, there is provided a power adaptive control system for a dredging robot underwater operation. The system adopts the above-mentioned power adaptive control method for a dredging robot underwater operation. The system includes:

[0033] A data acquisition module for collecting dredging robot underwater operation data, including historical operation time and the corresponding operation area, and determining the relationship between the historical operation time and the operation area;

[0034] A data processing module for processing the data collected by the data acquisition module to obtain a power adaptive control scheme;

[0035] Among them, the processing of the data collected by the data acquisition module includes:

[0036] Determine the operation time of the area to be operated this time according to the relationship between the historical operation time and the area of the operation area, and the area of the area to be operated;

[0037] Scan the terrain of the underwater area to be operated and estimate the operation difficulty;

[0038] Establish the power distribution model of the dredging robot according to the operation time, the area of the area to be operated and the operation difficulty, and perform power adaptive control according to the distribution model.

[0039] The present invention has the following technical effects:

[0040] When the present invention uses a dredging robot for underwater operations, it first obtains historical data and processes the data; uses a lidar to obtain the elevation data of the silt in the river channel and calculates the volume of the silt in the area to be operated, classifies the area to be operated according to the operation difficulty, and adopts different power adaptive control methods for different operation difficulty levels, which can handle non-linear and multi-variable coupled underwater operation scenarios and improve the operation reliability of the dredging robot. Description of the Drawings

[0041] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0042] Figure 1 It is a flowchart of a method for power adaptive control of underwater operation of a dredging robot provided by an embodiment of the present invention. Detailed Embodiments

[0043] To make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present invention.

[0044] Embodiment 1, as shown in the attached Figure 1 shows a flowchart of a method for power adaptive control of underwater operation of a dredging robot. As shown in the attached Figure 1 figure, a method for power adaptive control of underwater operation of a basic dredging robot includes:

[0045] S1: Collect the underwater operation data of the dredging robot, including the historical operation time and the corresponding historical operation area, and determine the relationship between the historical operation time and the operation area.

[0046] Among them, in this embodiment, the relationship formula between the historical operation time and the historical operation area can be obtained by linear fitting.

[0047] The underwater operation data of the dredging robot also includes historical operation power distribution data. Based on the historical operation time, historical operation area, and historical operation power distribution data, a neural network power adaptive control model is established. In this embodiment, with the historical operation time and historical operation area as inputs and the historical operation power distribution data as outputs, the neural network power adaptive control model is trained and established.

[0048] S2: Determine the operation time of the current area to be operated according to the relationship between the historical operation time and the historical operation area, and the area to be operated.

[0049] Among them, in this embodiment, by inputting the area to be operated into the relationship formula between the historical operation time and the historical operation area, the operation time of the current area to be operated can be determined.

[0050] S3: Scan the underwater terrain of the area to be operated and estimate the operation difficulty.

[0051] The specific steps include: S31: Divide the area to be operated into N blocks on average, where N>4; use lidar to measure the underwater terrain of the area to be operated and obtain N elevation data sets.

[0052] Among them, in this embodiment, the lidar uses a green pulsed laser source to illuminate the target scene, and the reflected pulsed illumination is detected by a single-photon detector array, which can distinguish the photons reflected by the target and the photons reflected by the particles in the water, making it particularly suitable for 3D imaging in highly turbid water.

[0053] S32: Collect the lowest elevation data in the N elevation data sets and calculate the average value to obtain the elevation calibration value T of the area to be operated.

[0054] S33: The control module of the dredging robot is embedded with GIS software. Based on the elevation calibration value T, a three-dimensional model of the underwater sludge is built, and the sludge volume Vn of the N areas to be operated is calculated.

[0055] S34: Divide the operation difficulty of the N areas to be operated into easy, medium, and difficult according to the sludge volume Vn.

[0056] In this embodiment, during the process of the dredging robot operating in the river channel for dredging, when the volume of silt is large, the dredging difficulty increases, and the previous power distribution may affect the dredging efficiency. Therefore, the volume of silt needs to be considered as a factor for additional power distribution. When the volume of silt is large, the power is adaptively adjusted, which can reduce the power of the underwater propulsion device of the dredging robot and allocate more power to the silt cleaning and silt conveying devices to complete the dredging work efficiently and stably.

[0057] S4: Establish a power distribution model for the dredging robot according to the time to be worked, the area of the area to be worked, and the working difficulty, and perform power adaptive control according to the distribution model;

[0058] Specifically, the steps include S41: The control module obtains the working difficulty of the area to be worked;

[0059] S42: The control module distributes power according to the working difficulty;

[0060] Among them, in this embodiment, when the working difficulty is easy, based on the time to be worked and the area of the area to be worked, a neural network control model is used to determine the power adaptive control strategy; this neural network model is established by training with the historical operation data of the dredging robot. When the working difficulty is easy, the river channel silt is relatively flat, and there is no need to consider the influence of the silt volume on the power adaptive control.

[0061] In this embodiment, when the working difficulty is medium, an expert PID control model is established by using domain expert experience or machine learning of the underwater operation data of the dredging robot. The time to be worked, the area of the area to be worked, and the volume Vn are mapped to power adjustment parameters to dynamically adjust the power adaptive control strategy. The expert PID control model uses domain expert experience or machine learning of the underwater operation data of the dredging robot to generate power adaptive control rules. The mapping to power adjustment parameters adjusts the parameters of the expert PID control model through the changes in the time to be worked, the area of the area to be worked, and the volume Vn. The expert PID control model is suitable for nonlinear systems and can handle power distribution under medium working difficulties.

[0062] In this embodiment, when the working difficulty is difficult, a reinforcement learning model is used. The time to be worked, the area of the area to be worked, and the volume Vn are used as state observation inputs to obtain the optimal power adaptive control strategy to balance performance and energy consumption.

[0063] The state observation module collects the time to be worked, the area of the area to be worked, and the volume Vn to describe the current environmental state;

[0064] An action selection module that determines the current power adaptive control strategy based on the current environmental state through a pre-determined strategy or a random strategy;

[0065] A reward feedback module that obtains a reward signal based on the feedback of the current environmental state;

[0066] Exemplarily, when the current environmental state changes, such as when the area to be worked decreases and the working time increases, a feedback reward signal is given.

[0067] A strategy update module that establishes a deep neural network based on the reward signal to update the parameters of reinforcement learning and obtain the optimal power adaptive control strategy;

[0068] Exemplarily, for example, when the area to be worked decreases and the working time increases, the updated current environmental state is input into a pre-trained deep neural network to output the parameters of reinforcement learning, and the current power adaptive control strategy can preferentially allocate power to the propulsion device.

[0069] S43: The control module allocates fixed power values to the auxiliary device and the safety device.

[0070] Among them, the auxiliary device includes a camera, a lighting lamp, a sonar, and a lidar; the safety device includes a floating system and a fault protection system, which are the keys to protecting the safe and stable operation of the dredging robot. Therefore, regardless of the operation difficulty, fixed power values are allocated to the auxiliary device and the safety device.

[0071] Embodiment 2, the present invention also provides a power adaptive control system for underwater operation of a dredging robot. The system adopts a power adaptive control method for underwater operation of a dredging robot in Embodiment 1. The system includes:

[0072] A data acquisition module for acquiring underwater operation data of the dredging robot, including historical working time and the corresponding working area, and determining the relationship between the historical working time and the working area;

[0073] A data processing module for processing the data acquired by the data acquisition module to obtain a power adaptive control scheme;

[0074] Among them, the processing of the data acquired by the data acquisition module includes:

[0075] Determining the working time of the current area to be worked according to the relationship between the historical working time and the working area, and the area of the area to be worked;

[0076] Scanning the terrain of the underwater area to be worked and estimating the operation difficulty;

[0077] Based on the time to be worked, the area of the area to be worked, and the working difficulty, a power distribution model of the dredging robot is established, and power adaptive control is performed according to the distribution model.

[0078] It should be noted that the terms used in the present invention are only for describing specific embodiments and do not limit the scope of the present application. As shown in the specification of the present invention, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method or device including the element.

[0079] It should also be noted that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "mounted", "connected", "coupled" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. An underwater operation power adaptive control method for a dredging robot, characterized in that, Including: S1: Collect the underwater operation data of the dredging robot, including the historical operation time and the corresponding historical operation area, and determine the relationship between the historical operation time and the operation area; S2: Determine the operation time of the current operation area according to the relationship between the historical operation time and the historical operation area, and the area of the area to be operated; S3: Scan the underwater terrain of the area to be operated and estimate the operation difficulty; S4: Establish a power distribution model for the dredging robot according to the operation time, the area of the area to be operated and the operation difficulty, and perform power adaptive control according to the distribution model; In S4, establishing a power distribution model for the dredging robot includes: S41: The dredging robot includes a control module, a propulsion device, a dredging device, a conveying device, a communication device, an auxiliary device and a safety device; the control module obtains the operation difficulty of the area to be operated; S42: The control module distributes power according to the operation difficulty; in S42, the control module distributes power according to the operation difficulty, including: S421: When the operation difficulty is easy, based on the operation time and the area of the area to be operated, use the neural network power adaptive control model to determine the power adaptive control strategy; S422: When the operation difficulty is medium, use the expert PID control model to map the operation time, the area of the area to be operated and the volume Vn of the area to be operated into power adjustment parameters, and dynamically adjust the power adaptive control strategy; S423: When the operation difficulty is difficult, use the reinforcement learning model to take the operation time, the area of the area to be operated and the volume Vn as state observation inputs, and obtain the optimal power adaptive control strategy to balance performance and energy consumption; S43: The control module assigns a fixed power value to the auxiliary device and the safety device.

2. The underwater operation power adaptive control method of a dredging robot according to claim 1, characterized in that The auxiliary device includes a camera, a lighting lamp, a sonar and a lidar; the safety device includes a floating system and a fault protection system.

3. A power adaptive control method for underwater operation of a dredging robot according to claim 2, characterized in that, S1 further includes: [[ID= 4. A method for power adaptive control of an underwater operation of a dredging robot according to claim 2, characterized in that, ​ ​ ​ ​ ​ 5. A method for power adaptive control of an underwater operation of a dredging robot according to claim 1, characterized in that, ​ 6. The underwater operation power adaptive control method of a dredging robot according to claim 5, characterized in that, The mapping is a power adjustment parameter, and the parameters of the expert PID control model are adjusted by changing the to-be-operated time, the to-be-operated area, and the volume Vn.

7. A method for power adaptive control of an underwater operation of a dredging robot according to claim 1, characterized in that, The reinforcement learning model includes: A state observation module that collects the to-be-operated time, the to-be-operated area, and the volume Vn to describe the current environmental state; An action selection module that determines the current power adaptive control strategy based on the current environmental state through a pre-determined strategy or a random strategy; A reward feedback module that obtains a reward signal according to the feedback of the current environmental state; A policy update module that establishes a deep neural network according to the reward signal to update the parameters of the reinforcement learning and obtain the optimal power adaptive control strategy.

8. An underwater operation power adaptive control system for a dredging robot, characterized in that, The system adopts a method for power adaptive control of underwater operation of a dredging robot according to any one of claims 1-7. The system includes: A data acquisition module for collecting underwater operation data of the dredging robot, including the historical operation time and the corresponding historical operation area, and determining the relationship between the historical operation time and the historical operation area; A data processing module for processing the data collected by the data acquisition module to obtain a power adaptive control scheme; Among them, the processing of the data collected by the data acquisition module includes: Determining the to-be-operated time of the current to-be-operated area according to the relationship between the historical operation time and the historical operation area, and the to-be-operated area; Scanning the terrain of the underwater to-be-operated area to estimate the operation difficulty; Establishing a power distribution model for the dredging robot according to the to-be-operated time, the to-be-operated area, and the operation difficulty, and performing power adaptive control according to the distribution model.

Images